To see the other types of publications on this topic, follow the link: Amharic language.
Journal articles on the topic 'Amharic language'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Amharic language.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Retta, Ephrem Afele, Richard Sutcliffe, Jabar Mahmood, Michael Abebe Berwo, Eiad Almekhlafi, Sajjad Ahmad Khan, Shehzad Ashraf Chaudhry, Mustafa Mhamed, and Jun Feng. "Cross-Corpus Multilingual Speech Emotion Recognition: Amharic vs. Other Languages." Applied Sciences 13, no. 23 (November 22, 2023): 12587. http://dx.doi.org/10.3390/app132312587.
Full textAbstract:
In a conventional speech emotion recognition (SER) task, a classifier for a given language is trained on a pre-existing dataset for that same language. However, where training data for a language do not exist, data from other languages can be used instead. We experiment with cross-lingual and multilingual SER, working with Amharic, English, German, and Urdu. For Amharic, we use our own publicly available Amharic Speech Emotion Dataset (ASED). For English, German and Urdu, we use the existing RAVDESS, EMO-DB, and URDU datasets. We followed previous research in mapping labels for all of the datasets to just two classes: positive and negative. Thus, we can compare performance on different languages directly and combine languages for training and testing. In Experiment 1, monolingual SER trials were carried out using three classifiers, AlexNet, VGGE (a proposed variant of VGG), and ResNet50. The results, averaged for the three models, were very similar for ASED and RAVDESS, suggesting that Amharic and English SER are equally difficult. Similarly, German SER is more difficult, and Urdu SER is easier. In Experiment 2, we trained on one language and tested on another, in both directions for each of the following pairs: Amharic↔German, Amharic↔English, and Amharic↔Urdu. The results with Amharic as the target suggested that using English or German as the source gives the best result. In Experiment 3, we trained on several non-Amharic languages and then tested on Amharic. The best accuracy obtained was several percentage points greater than the best accuracy in Experiment 2, suggesting that a better result can be obtained when using two or three non-Amharic languages for training than when using just one non-Amharic language. Overall, the results suggest that cross-lingual and multilingual training can be an effective strategy for training an SER classifier when resources for a language are scarce.
2
Kifleyesus, Abbebe. "The Argobba of Ethiopia are not the Language they Speak." Aethiopica 9 (September 24, 2012): 7–22. http://dx.doi.org/10.15460/aethiopica.9.1.238.
Full textAbstract:
The Argobba of southeastern Wällo and northeastern Šäwa live amongst and speak the languages of the Amhara and the Oromo with great ease as if they are members of these ethnic groups. For them Amharic and Afaan Oromoo are the languages of administration and market transaction and therefore important for Argobba survival in a region domi-nated by these two ethno-linguistic groups. Yet the Argobba I met in these lands identified themselves as Argobba, and they were known as such, despite the fact that several of them had Amharic or Afaan Oromoo as their first language. The central claim of this article is therefore that the Argobba of this region define themselves as Argobba based on their traditions, customs, beliefs, values, and total cultural practices and not on the basis of who can or cannot speak the Argobba language.
3
Mekonnen, A. M., and E. Hussien. "Stylistic Motivation in Amharic Media Language Use." Язык и текст 10, no. 2 (June 29, 2023): 38–56. http://dx.doi.org/10.17759/langt.2023100204.
Full textAbstract:
<p>This article looked into the stylistic motivations of English words used in Amharic media. It used the qualitative descriptive approach to examine the data of this research so as to be able to investigate the stylistic motivation of language use in the Amharic media programs that are concerned with sport, medical science, and science and technology. Purposive sampling was used to select these programs, resulting in 1090 bilingual extracts. The English words were given due focus to examine the stylistic motivation that they have served in the Amharic media. In this study, it is found that there are numerous examples of English borrowing used in the Amharic media because they are shorter and more economical (i.e., for their brevity) than their Amharic counterparts. It is also found in this study that English loan words are used in Amharic media in order to precise some words for which there is no unequivocal Amharic equivalent. Employing variation of expression to avoid tedious recurrence of words in Amharic media is another finding in this study. Therefore, three aspects of the stylistic motivation developed by Galinsky are found to be available in the Amharic media language.</p>
4
Yeshambel, Tilahun, Josiane Mothe, and Yaregal Assabie. "Amharic Adhoc Information Retrieval System Based on Morphological Features." Applied Sciences 12, no. 3 (January 26, 2022): 1294. http://dx.doi.org/10.3390/app12031294.
Full textAbstract:
Information retrieval (IR) is one of the most important research and development areas due to the explosion of digital data and the need of accessing relevant information from huge corpora. Although IR systems function well for technologically advanced languages such as English, this is not the case for morphologically complex, under-resourced and less-studied languages such as Amharic. Amharic is a Semitic language characterized by a complex morphology where thousands of words are generated from a single root form through inflection and derivation. This has made the development of Amharic natural language processing (NLP) tools a challenging task. Amharic adhoc retrieval also faces challenges due to scarcity of linguistic resources, tools and standard evaluation corpora. In this research work, we investigate the impact of morphological features on the representation of Amharic documents and queries for adhoc retrieval. We also analyze the effects of stem-based and root-based text representation, and proposed new Amharic IR system architecture. Moreover, we present the resources and corpora we constructed for evaluation of Amharic IR systems and other NLP tools. We conduct various experiments with a TREC-like approach for Amharic IR test collection using a standard evaluation framework and measures. Our findings show that root-based text representation outperforms the conventional stem-based representation on Amharic IR.
5
Taye, Bekau Atnafu. "The medium of instruction in Ethiopian Higher Education Institutions: Kotebe Metropolitan University Case study." African Journal of Teacher Education 8 (April 1, 2019): 1–24. http://dx.doi.org/10.21083/ajote.v8i0.4367.
Full textAbstract:
The aim of this article is to examine the medium of instruction in Ethiopian higher education institutions and the perceived consequences of the failure to learn a lingua franca. The study was qualitative and it used interviews and focus group discussions (FGDs). Five teachers and five students took part in the interviews and six teachers and six students participated in the FGDs. The findings of the study showed that the role of Amharic as a working language has not been given recognition despite the fact that Amharic was constitutionally granted to be a working language. Due to language barriers, students who are speakers of Oromipha and other languages from the Eastern and Western parts of Ethiopia suffer passivity in the classroom because they do not speak Amharic although Amharic has been taught as a subject in all regional states of the country. Increased identity politics seems to have generated a negative attitude towards Amharic, Ethiopia's former official lingua franca. Non-Amharic native speakers appeared to lose interest in learning Amharic while they were in primary and secondary schools. The absence of an official, common language which could be used for wider communication in higher education has resulted in having challenges among the student population.
6
E.H., Emam, and A. M. Mekonnen. "Patterns of Code-switching in the Amharic Media." Macrolinguistics 10, no. 17 (December 31, 2022): 125–50. http://dx.doi.org/10.26478/ja2022.10.17.6.
Full textAbstract:
This study examines patterns of Amharic-English code-switching in the Amharic media language use. It employed a qualitative descriptive approach, which helped break down the recordings and transcripts into intelligible units that helped explain the various language use forms created by code-switching in the Amharic media. Thus, five Amharic media outlets focusing on sport, medical science, and science and technology were purposively selected to study language use in the Amharic media. Hence, 1090 examples which have both Amharic and English elements were selected. A generic step of data analysis was made so as to classify the different types and patterns of code-switching instances. The findings indicated that the three different types of code-switching, namely tag switching, inter-sentential code-switching, and intra-sentential code-switching, are found in the Amharic media language use. Moreover, it was found that there are different patterns of code-switching from English to Amharic. Thus, it is shown that Amharic is the matrix language and is quite resistant against any change of its basic word order. It can also be seen that the mixed constituents found in the Amharic media confirm that the matrix language frame (MLF) model can satisfactorily explain the patterns of Amharic-English code-switching.
7
Lusini, Gianfrancesco. "Lingua letteraria e lingua di corte: diglossia e insegnamento tradizionale in Etiopia fra Tardo Antico e Medio Evo." AION (filol.) Annali dell’Università degli Studi di Napoli “L’Orientale” 41, no. 1 (December 20, 2019): 274–84. http://dx.doi.org/10.1163/17246172-40010020.
Full textAbstract:
Abstract The Ethiopian literary tradition extends over a time frame beginning even before the christianization of the Country (first half of the 4th cent.) up to modern times. In this long period we frequently register phenomena of interference both among different languages (Greek, Gǝ‘ǝz, Arabic, Amharic, agaw languages and so on) and between various registers of the same language, produced or conditioned by specific cultural or religious contexts. Particularly, in the Middle Ages the differentiation between Gǝ‘ǝz as the language of the clergy and the written discourse, and Amharic as the language of the court and the verbal communication, had momentous reflexes on the traditional teaching, related to Gǝ‘ǝz liturgical texts, but orally transmitted in Amharic. This development proved to be crucial for the start of the literarization process of Amharic, to be dated back to the second half of the 16th cent., as an effect of the missionary propaganda of the Portuguese Jesuits and of their polemics against the Ethiopian Orthodox clergy.
8
Hailay Tesfay. "PRACTICALITY OF ALTERNATIVE ASSESSMENTS: FROM AMHARIC LANGUAGE INSTRUCTORS’ VIEW POINTS." Ethiopian Journal of Business and Social Science 1, no. 2 (August 1, 2018): 95–112. http://dx.doi.org/10.59122/1342ace.
Full textAbstract:
The purpose of this study was examining the practicality of Alternative Assessment in Ethiopian higher education Amharic Language educational context. The study also, endeavors to seek the challenges (barriers) of Alternative Assessment. In order to achieve the goals of the present study, the researcher used Assessment practices questionnaire and in-depth interview instruments. The data were collected from 35 Amharic Language instructors, teaching at different higher Education institutions. The data were analyzed through the mixed methods. The Quantitative result of both gender and level of profession, the study indicated that the practicality of Alternative assessment in higher education Amharic language context is averagely low. Also, according to Instructors’ viewpoints, the main barriers that hinder the practicality of Alternative assessment in higher Education are, time consuming, inappropriateness to correction and not suitable for grading. The study revealed that in spite of Amharic language instructors’ knowledge of Alternative Assessment and their agreement with Alternative Assessment implementation criteria, they rarely apply it in their Language context. Further researches should reveal why Amharic Language instructors are not interested in implementing Alternative assessment in their Language context. Key Terms: Alternative Assessments; Amharic language educational context; Amharic Language Instructors; Higher Education institutions
9
A., Getahun. "Morphosyntactic Structures of Existential, Possessive and Locative Constructions in Amharic." Macrolinguistics 9, no. 15 (December 31, 2021): 25–43. http://dx.doi.org/10.26478/ja2021.9.15.2.
Full textAbstract:
This paper lays out the morphosyntactic structures of existential, locative and possessive constructions in Amharic. Amharic belongs to South Ethio-Semitic language subfamily. It is natively spoken in the Amhara region and used as the first and the second language for some urban dwellers in the country. It is a working language for the Federal Government of Ethiopia. It serves the same in Gambella, Southern Nations, Nationalities and Peoples’ and Benishangul-Gumuz regional states. The Amharic existential, possessive and locative constructions are characterized by using the same existential verb stem all-‘exist’. The verb is defective in its derivation and conjugation. Unlike the prototypical verbs of the language, the existential verb uses a different verb for imperfective and past verb forms. Unlike the regular verbs of the language, the existential verb, which is perfective in form, conveys present tense. It has been observed that indefinite nominals appear as the E (Existent) in existentials and possessives, whereas definite ones appear in locatives. The morphosyntactic features of existentials and locatives are the same in every aspect except the use of definiteness of the E (Existent). The possessives differ from the two constructions in word order and morphological structure of the verb.
10
Hayward, Katrina, and Richard J. Hayward. "Amharic." Journal of the International Phonetic Association 22, no. 1-2 (June 1992): 48–52. http://dx.doi.org/10.1017/s0025100300004606.
Full text
11
ullendorff, edward. "a tigrinya letter from an eritrean notable." Bulletin of the School of Oriental and African Studies 68, no. 2 (June 2005): 295–97. http://dx.doi.org/10.1017/s0041977x05000145.
Full textAbstract:
tigrinya (t[schwa]gr[schwa]ňňa) is, next to amharic, the most widely spoken semitic language in ethiopia, mainly in the tigre province and in eritrea. in most respects it is closer to the orthodox semitic typology than amharic. in terms of the number of semitic language speakers in general it follows arabic and amharic and surpasses hebrew by those who speak that language indigenously.
12
Hailu, Yemserach Legesse. "Language Law and Policy of the Federal Government of Ethiopia: Implications for Fair Trial and the Rights of Non-Amharic Language Speakers Accused." Acta Humana 9, no. 1 (March 31, 2021): 59–76. http://dx.doi.org/10.32566/ah.2021.1.4.
Full textAbstract:
Ethiopia is a multilingual country with a federal form of state structure. The 1995 Constitution of the Federal Democratic Republic of Ethiopia (FDRE Constitution) gave equal recognition for all Ethiopian languages, but has chosen Amharic to become the working language of the Federal Government. In order to accommodate the needs of non-Amharic speakers in the provision of public services, the Constitution and other laws such as the Criminal Procedure Code, require the use of interpreters. Particularly in criminal proceedings, non-Amharic speakers are entitled to be assisted with a ‘qualified’ interpreter to meaningfully participate in the cases. In practice, it is observed that accused people who do not speak the working language of the federal government are unable to effectively understand or get prompt and detailed information regarding the nature and effect of the case brought against them. Even if they know the case, they are not able to effectively explain their defences to the court or associated bodies, and thereby defend their rights. This study reveals that non-Amharic speakers are not effectively served according to the legal standards. This problem subsists mainly due to the absence or limited number of interpreters, as well as the use of untrained interpreters. Despite some efforts to address the problem, the federal government has not yet laid down any formal mechanism by which people with limited and/or no Amharic language proficiency are properly served in criminal proceedings both before and during trial. This study proposes the federal government to establish court interpreter training institutions and to standardise court interpretation by allocating the necessary budget; lay down a formal mechanism such as enacting detailed laws and working manuals for assigning interpreters; providing other local languages the status of working language; consulting interpretation technologies and working in collaboration with different stakeholders.
13
Endalie, Demeke, Getamesay Haile, and Wondmagegn Taye. "Deep learning-based idiomatic expression recognition for the Amharic language." PLOS ONE 18, no. 12 (December 14, 2023): e0295339. http://dx.doi.org/10.1371/journal.pone.0295339.
Full textAbstract:
Idiomatic expressions are built into all languages and are common in ordinary conversation. Idioms are difficult to understand because they cannot be deduced directly from the source word. Previous studies reported that idiomatic expression affects many Natural language processing tasks in the Amharic language. However, most natural language processing models used with the Amharic language, such as machine translation, semantic analysis, sentiment analysis, information retrieval, question answering, and next-word prediction, do not consider idiomatic expressions. As a result, in this paper, we proposed a convolutional neural network (CNN) with a FastText embedding model for detecting idioms in an Amharic text. We collected 1700 idiomatic and 1600 non-idiomatic expressions from Amharic books to test the proposed model’s performance. The proposed model is then evaluated using this dataset. We employed an 80 by 10,10 splitting ratio to train, validate, and test the proposed idiomatic recognition model. The proposed model’s learning accuracy across the training dataset is 98%, and the model achieves 80% accuracy on the testing dataset. We compared the proposed model to machine learning models like K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Random Forest classifiers. According to the experimental results, the proposed model produces promising results.
14
Mengistu, Abrham Debasu, and Dagnachew Melesew Alemayehu. "Text Independent Amharic Language Speaker Identification in Noisy Environments using Speech Processing Techniques." Indonesian Journal of Electrical Engineering and Computer Science 5, no. 1 (January 1, 2017): 109. http://dx.doi.org/10.11591/ijeecs.v5.i1.pp109-114.
Full textAbstract:
<p>In Ethiopia, the largest ethnic and linguistic groups are the Oromos, Amharas and Tigrayans. This paper presents the performance analysis of text-independent speaker identification system for the Amharic language in noisy environments. VQ (Vector Quantization), GMM (Gaussian Mixture Models), BPNN (Back propagation neural network), MFCC (Mel-frequency cepstrum coefficients), GFCC (Gammatone Frequency Cepstral Coefficients), and a hybrid approach had been use as techniques for identifying speakers of Amharic language in noisy environments. For the identification process, speech signals are collected from different speakers including both sexes; for our data set, a total of 90 speakers’ speech samples were collected, and each speech have 10 seconds duration from each individual. From these speakers, 59.2%, 70.9% and 84.7% accuracy are achieved when VQ, GMM and BPNN are used on the combined feature vector of MFCC and GFCC. </p>
15
Krzyżanowska, Magdalena. "Mäsob: Designing a new Amharic coursebook." Afrika und Übersee 93 (December 31, 2020): 224–38. http://dx.doi.org/10.15460/auue.2020.93.1.213.
Full textAbstract:
This article presents a project to design a new Amharic coursebook which draws upon current approaches to language teaching, and will provide stimulating learning materials for its users. The coursebook will target university students at A1 level, and in its content and structure will aim, for the first time in the history of Amharic language teaching, to conform to the spirit of the Common European Framework of Reference for Languages. Topic-based and task-based syllabi will form the backbone of the coursebook. It will contain a range of activities in which students, while learning grammar, are engaged in using new language in a meaningful, communicative way. Apart from developing the usual four language skills, among which priority will be given to oral practice, the coursebook will help students to acquire cultural competence and support them in improving their language learning strategies.
16
Mulu, Alemebante, and Vishal Goyal. "Context-Based Text Completion System for Amharic Language." JOURNAL OF SCIENTIFIC RESEARCH 66, no. 03 (2022): 212–18. http://dx.doi.org/10.37398/jsr.2022.660326.
Full textAbstract:
This paper discusses the practical aspects of easiness in communication using Short Message Service (SMS), E-mailing, correcting misspelt words and checking the grammatical mistakes. There are different data entry mechanisms to insert a text on the computer machine as well as a mobile device, such as a keyboard, soft keys, speech etc. The paper proposed to develop a contextbased auto text completion system for the Amharic language specifically to correct misspelling on Short Message Service (SMS), E-mailing and helps to correct the grammar mistakes as well. Data entry technique can be inserted with the support of text completion (predictive) or non-predictive. Therefore, we are using a statistical model, Predictive Partial Match (PPM) and Support Vector Machine (SVM) approaches for implementing the Amharic contextbased text completion system. Since the system is developed by using the context-based and statistical model, we adopted the Amharic Part of Speech (POS) tagger system. For training and testing the system, we are using 395,464 unique words with frequency and 750,000 sentences that has been prepared by the Walta Information Centre (WIA) and Ethiopia News Agency (ENA). All those data have been used to build the Amharic dictionary, the corpus of the system and to calculate the frequency occurrences of each word as well. Finally, the results show a 14% improvement from traditional frequency-based Amharic word prediction system.
17
Salih, Mohammed Hassen, Lena Wettergren, Helena Lindgren, Kerstin Erlandsson, Hussen Mekonen, and Lemma Derseh. "Translation and psychometric evaluation of chronic illness anticipated stigma scale (CIASS) among patients in Ethiopia." PLOS ONE 17, no. 1 (January 21, 2022): e0262744. http://dx.doi.org/10.1371/journal.pone.0262744.
Full textAbstract:
Background Stigma is common among patients with chronic illnesses. It affects the delivery of healthcare for not addressing the psychological components and may interfere with the patient’s attendance to necessary health care services. Therefore, a valid and reliable instrument to measure anticipated stigma related to chronic illness is vital to inform possible interventions. This study aimed to translate the Chronic Illness Anticipated Stigma Scale (CIASS) into the Amharic language and evaluate its psychometric properties in Ethiopia. Methods The CIASS was translated into Amharic language using standard procedures. The Amharic version was completed by 173 patients (response rate 96%) with chronic illness from three referral hospitals in the Amhara region. Internal consistency was examined through Cronbach’s alpha. Construct validity was evaluated by confirmatory factor analysis and convergent validity by using a Pearson correlation of P-value less than or equal to 0.05. Results The internal consistency was estimated at Cronbach alpha of 0.92. By using a structural equation model, and modification indices a model fitness testing was run and shows a root mean squared error of approximation 0.049 (90% CI, 0.012–0.075). The structural validity results in 78.8% of confirmatory factor analysis showed from the extraction of the three-dimension (components). Validity tests for convergent by using Pearson correlation positively correlated with common mental distress and negatively correlated with quality of life–BREF, and the construct validity shows a good valid tool to CIASS. Conclusion The Amharic language version of the chronic illness anticipated stigma scale shows a satisfactory level of reliability and validity on different psychometric measures of assessment. The tool may be useful for future researchers and patients with chronic illness in the Amharic-speaking population. Moreover, it will be used to see the psychological burden related to chronic illness and for comparison among international population groups.
18
Drewes, A. J. "Amharic as a language of Islam." Bulletin of the School of Oriental and African Studies 70, no. 1 (February 2007): 1–62. http://dx.doi.org/10.1017/s0041977x07000018.
Full textAbstract:
Amharic, the native language of a large group of the population of central Ethiopia, also functions as a lingua franca among the neighbouring peoples, and has done so for a long time. The language is usually associated with the culture of the politically dominant part of the population, the Christian culture. But it is certain that from the mid-nineteenth century onwards, and probably even before that time, Amharic was used also for Islamic religious texts: poetry composed to spread the basic religious concepts of Islam and songs to be chanted in religious meetings. The first foreign scholar to become aware of this was Enrico Cerulli, who published some examples of Islamic songs in Amharic in 1926. Much more has since been published by Ethiopians. In the 1960s I obtained a small collection of such texts which are discussed in this article.
19
Yeshambel, Tilahun, Josiane Mothe, and Yaregal Assabie. "Learned Text Representation for Amharic Information Retrieval and Natural Language Processing." Information 14, no. 3 (March 20, 2023): 195. http://dx.doi.org/10.3390/info14030195.
Full textAbstract:
Over the past few years, word embeddings and bidirectional encoder representations from transformers (BERT) models have brought better solutions to learning text representations for natural language processing (NLP) and other tasks. Many NLP applications rely on pre-trained text representations, leading to the development of a number of neural network language models for various languages. However, this is not the case for Amharic, which is known to be a morphologically complex and under-resourced language. Usable pre-trained models for automatic Amharic text processing are not available. This paper presents an investigation on the essence of learned text representation for information retrieval and NLP tasks using word embeddings and BERT language models. We explored the most commonly used methods for word embeddings, including word2vec, GloVe, and fastText, as well as the BERT model. We investigated the performance of query expansion using word embeddings. We also analyzed the use of a pre-trained Amharic BERT model for masked language modeling, next sentence prediction, and text classification tasks. Amharic ad hoc information retrieval test collections that contain word-based, stem-based, and root-based text representations were used for evaluation. We conducted a detailed empirical analysis on the usability of word embeddings and BERT models on word-based, stem-based, and root-based corpora. Experimental results show that word-based query expansion and language modeling perform better than stem-based and root-based text representations, and fastText outperforms other word embeddings on word-based corpus.
20
Asemie, Smegnew, Kassahun Azezew, and Birhanu Gardie. "Design and Develop Amharic Language Interface to Database." Indian Journal of Science and Technology 14, no. 44 (November 21, 2021): 3254–63. http://dx.doi.org/10.17485/ijst/v14i44.1178.
Full text
21
Kayam, Orly. "Language and Culture." Studies in English Language Teaching 3, no. 4 (December 29, 2015): 500. http://dx.doi.org/10.22158/selt.v3n4p500.
Full textAbstract:
<p><em>The study focuses on Ethiopian Jewish women’s struggles with language usage and social adaptation. The study aims to (a) evaluate the importance of knowledge and usage of Amharic in their daily lives, (b) evaluate the importance of knowledge and usage of Hebrew in their daily lives and (c) identify the differences in Israeli and Ethiopian Jewish cultures. The study was based on data collected and analyzed from a questionnaire that was distributed to a class of Ethiopian Jewish women who study English at a school in Netanya, Israel. The findings showed that while all of the participants speak Amharic, there are differences in literacy in Amharic among them. All of them have difficulties in Hebrew, but see Hebrew as the vehicle for upward mobility within Israeli society. They view Israeli culture as one that is lacking in politeness, respect and dignity, which is very much part of the fabric of the Ethiopian Jewish lifestyle. There is also a strong desire to preserve the past by preserving their language. This study promotes a new dimension to the study of Ethiopian Jewish women (Kayam </em><em>&</em><em> Hirsch, in press) in that it adds to the study of language acquisition in the immigrant setting.</em><em></em></p>
22
Emiru, Eshete Derb, Shengwu Xiong, Yaxing Li, Awet Fesseha, and Moussa Diallo. "Improving Amharic Speech Recognition System Using Connectionist Temporal Classification with Attention Model and Phoneme-Based Byte-Pair-Encodings." Information 12, no. 2 (February 3, 2021): 62. http://dx.doi.org/10.3390/info12020062.
Full textAbstract:
Out-of-vocabulary (OOV) words are the most challenging problem in automatic speech recognition (ASR), especially for morphologically rich languages. Most end-to-end speech recognition systems are performed at word and character levels of a language. Amharic is a poorly resourced but morphologically rich language. This paper proposes hybrid connectionist temporal classification with attention end-to-end architecture and a syllabification algorithm for Amharic automatic speech recognition system (AASR) using its phoneme-based subword units. This algorithm helps to insert the epithetic vowel እ[ɨ], which is not included in our Grapheme-to-Phoneme (G2P) conversion algorithm developed using consonant–vowel (CV) representations of Amharic graphemes. The proposed end-to-end model was trained in various Amharic subwords, namely characters, phonemes, character-based subwords, and phoneme-based subwords generated by the byte-pair-encoding (BPE) segmentation algorithm. Experimental results showed that context-dependent phoneme-based subwords tend to result in more accurate speech recognition systems than the character-based, phoneme-based, and character-based subword counterparts. Further improvement was also obtained in proposed phoneme-based subwords with the syllabification algorithm and SpecAugment data augmentation technique. The word error rate (WER) reduction was 18.38% compared to character-based acoustic modeling with the word-based recurrent neural network language modeling (RNNLM) baseline. These phoneme-based subword models are also useful to improve machine and speech translation tasks.
23
Mulugeta, Teferi, and Bye Yimam. "syntax of Amharic ideophones." Macrolinguistics and Microlinguistics 3, no. 1/2 (December 31, 2022): 1–14. http://dx.doi.org/10.21744/mami.v3n1/2.28.
Full textAbstract:
This study is on Amharic ideophones, a subject that has not been described well in the syntax of Amharic. The data used for the analysis are collected from natural settings of the Amharic-speaking community in Debre Birhan College of Teacher Education. The description shows that Amharic ideophones contradict some earlier generalizations made about the syntax of ideophones in such works which claim that ideophones do not fit in the grammar of other word classes in a language, and which states that ideophones do not enter any phrase structure, nor are they modified by other word classes. The description here shows that ideophones fit well into the grammar of the Amharic language. In contrast to such claims, they project different phrases such as noun phrases, which occur in subject and object positions and they can occur with or without a modifier. Their verb phrases appear with adverbial modifiers. Amharic ideophones can also be modifiers of nouns, verbs, and adjectives. They form complex predicates with auxiliaries. Their noun phrases come in dative, ablative and locative case forms. Ideophones occur in all types of sentences, suggesting that their distribution is unrestricted.
24
Solomon, Rodas, and Mesfin Abebe. "Amharic Language Image Captions Generation Using Hybridized Attention-Based Deep Neural Networks." Applied Computational Intelligence and Soft Computing 2023 (April 30, 2023): 1–11. http://dx.doi.org/10.1155/2023/9397325.
Full textAbstract:
This study aims to develop a hybridized deep learning model for generating semantically meaningful image captions in Amharic Language. Image captioning is a task that combines both computer vision and natural language processing (NLP) domains. However, existing studies in the English language primarily focus on visual features to generate captions, resulting in a gap between visual and textual features and inadequate semantic representation. To address this challenge, this study proposes a hybridized attention-based deep neural network (DNN) model. The model consists of an Inception-v3 convolutional neural network (CNN) encoder to extract image features, a visual attention mechanism to capture significant features, and a bidirectional gated recurrent unit (Bi-GRU) with attention decoder to generate the image captions. The model was trained on the Flickr8k and BNATURE datasets with English captions, which were translated into Amharic Language with the help of Google Translator and Amharic Language experts. The evaluation of the model showed improvement in its performance, with a 1G-BLEU score of 60.6, a 2G-BLEU score of 50.1, a 3G-BLEU score of 43.7, and a 4G-BLEU score of 38.8. Generally, this study highlights the effectiveness of the hybrid approach in generating Amharic Language image captions with better semantic meaning.
25
Yigzaw, Netsanet, Million Meshesha, and Chala Diriba. "A Generic Approach towards Amharic Sign Language Recognition." Advances in Human-Computer Interaction 2022 (September 22, 2022): 1–11. http://dx.doi.org/10.1155/2022/1112169.
Full textAbstract:
In the day-to-day life of communities, good communication channels are crucial for mutual understanding. The hearing-impaired community uses sign language, which is a visual and gestural language. In terms of orientation and expression, it is separate from written and spoken languages. Despite the fact that sign language is an excellent platform for communication among hearing-impaired persons, it has created a communication barrier between hearing-impaired and non-disabled people. To address this issue, researchers have proposed sign language to text translation systems for English and other European languages as a solution. The goal of this research is to design and develop an Amharic digital text converter system using Ethiopian sign language. The proposed system was created with the help of two key deep learning algorithms: a pretrained deep learning model and a Long Short-Term Memory (LSTM). The LSTM was used to extract sequence information from a sequence of image frames of a specific sign language, while the pretrained deep learning model was used to extract features from single frame images. The dataset used to train the algorithms was gathered in video format from Addis Ababa University. Prior to feeding the obtained dataset to the deep learning models, data preprocessing activities such as cleaning and video to image frame segmentation were conducted. The system was trained, validated, and tested using 80%, 10%, and 10% of the 2475 images created during the preprocessing step. Two pretrained deep learning models, EfficientNetB0 and ResNet50, were used in this investigation, and they attained an accuracy of 72.79%. In terms of precision and f1-score, ResNet50 outperformed EfficientNetB0. For the proposed system, a graphical user interface prototype was created, and the best performing model was chosen and implemented. The proposed system can be utilized as a starting point for other researchers to improve upon, based on the outcomes of the experiment. More high-quality training datasets and high-performance training machines, such as GPU-enabled computers, can be added to the system to improve it.
26
Chali, Keresa Kumera, and Andrea Parapatics. "Language Policy and Practices in an Ethiopian University towards Multilingualism." Languages 9, no. 6 (May 28, 2024): 198. http://dx.doi.org/10.3390/languages9060198.
Full textAbstract:
The study explores an Ethiopian higher education institution’s language policy and practices, explicitly focusing on multilingualism. Thе rеsеarch highlights a discrеpancy between languagе policy and classroom rеalitiеs. Despite English being officially designated as the primary instructional medium of higher education institutions, the prevalent environment for teaching and learning is multilingual, incorporating Afaan Oromoo, Amharic, and other languages alongside English. This disparity challеngеs thе monolingual languagе еducation policy mandatеd by thе Ethiopian constitution. The study employs a mixed-methods approach to offer a comprehensive perspective on the issue, stressing the necessity for a more holistic understanding of the situation. Furthеrmorе, thе rеsеarch indicatеs that thе Ethiopian constitution lacks еxplicit provisions addressing multilingualism within highеr еducation institutions, rеvеaling a gap in thе lеgal framework. This misalignmеnt calls for potential policy adjustmеnts to bеttеr accommodatе thе multilingual nature of highеr еducation. Bеyond thе classroom, both instructors and studеnts frеquеntly usе Afaan Oromoo, Amharic, and othеr hеritagе languagеs in thеir intеractions, furthеr еmphasizing thе importancе of undеrstanding thеsе languagе dynamics in thе Ethiopian highеr еducation contеxt. Ovеrall, this study undеrscorеs thе nееd for a closеr еxamination of languagе practicеs and thеir implications, offеring insights into promoting morе inclusivе еducation and informеd languagе policiеs within Ethiopian highеr еducation institutions.
27
Melkie, Tadesse Belayneh, Zelalem Mengistu Gashaw, Zelalem Ayichew Workineh, Tamiru Minwuye Andargie, Tibeb Zena Debele, and Solomon Gedlu Nigatu. "Translation, reliability, and validity of Amharic versions of the Pelvic Floor Distress Inventory (PFDI-20) and Pelvic Floor Impact Questionnaire (PFIQ-7)." PLOS ONE 17, no. 11 (November 17, 2022): e0270434. http://dx.doi.org/10.1371/journal.pone.0270434.
Full textAbstract:
Purpose Pelvic Floor Disorders (PFDs) affects many women and have a significant impact on their quality of life. Pelvic Floor Impact Questionnaire (PFIQ-7) and Pelvic Floor Distress Inventory (PFDI-20) help to assess PFDs; however, both are not culturally translated into the Amharic-language. Hence, we aimed to translate the English versions of short forms of the PFDI-20 and PFIQ-7 into Amharic-language and evaluate their psychometric properties in Amharic-speaking Ethiopian women with symptomatic PFDs. Methods The PFDI-20 and PFIQ-7 were translated into Amharic language using standard procedures. The Amharic versions were completed by 197 patients (response rate 92%) with PFDs from University of Gondar specialized and comprehensive Hospital. Internal consistency and test-retest reliability were examined through Cronbach’s alpha and Intraclass correlation coefficients (ICC). A relative criterion standard, POP-SS-7 score, was correlated with total PFDI-20 and subscale POPDI-6 scores using spearman’s rank order correlation (SCC). Construct validity was evaluated by known group validity using the Mann–Whitney U test. Results Both instruments were successfully translated and adapted with an excellent content validity (> 0.90). The Amharic versions of the PFDI-20 and PFIQ-7 showed excellent internal consistency and test-retest reliability in both summary and subscales (Cronbach’s alpha: 0.92 for PFDI-20 and 0.91 for PFIQ-7; and ICC: 0.97 for PFDI-20 and 0.86 for PFIQ-7). Criterion validity was good for POPDI-6 (SCC = 0.71; p < 0.001). Moreover, construct validity was acceptable, showing significant differences among groups of PFDs in the PFDI-20 and PFIQ-7 scores (Mann–Whitney U Test; p < 0.001). Conclusions The Amharic versions of the PFDI-20 and PFIQ-7 are comprehensible, reliable, valid, and feasible in Ethiopian Amharic-speaking women with PFDs to evaluate symptoms and its impact during research and clinical practice. However, further studies are needed to evaluate the responsiveness.
28
Gebremariam, Hailay Tesfay, and Abate Demissie Gedamu. "Assessment for learning strategies: Amharic Language Teachers’ Practice and Challenges in Ethiopia." International Journal of Language Education 6, no. 2 (June 30, 2022): 128. http://dx.doi.org/10.26858/ijole.v6i2.20505.
Full textAbstract:
Assessment is the central point of educational progress; it is the assistant to teachers during and after teaching and learning. One of the assessment genres, assessment for learning is referred to gathering information during teaching and learning, to determine students’ success in learning. The study aims to determine the understanding of assessment for learning strategies and challenges may face in Amharic language teachers. The participants selected from all levels of general education (1-12 grades), through cluster random sampling, were 180 Amharic language teachers for a questionnaire survey. In addition, twelve (12) teachers and four (4) teachers were selected through cluster random sampling respectively for an interview and informal conversation. The data acquired through the closed-ended questionnaire was analyzed by a one-sample t-test, while the data obtained through an open-ended questionnaire; interviews and informal conversations were analyzed in qualitative verbal description. The results are presented in two ways; the data from the close-ended questionnaire shows that Amharic language teachers are practice assessment for learning strategies in the classrooms, which is statistically significant (P < 0.01). On the other hand, the data from the open-ended questionnaire shows most Amharic language teachers’ reliance is on the old form of assessment and their awareness assessment for learning strategies is limited. In addition, the challenges, based on the practice of assessment for learning strategies in faced in the language classrooms; lack of transparency, lack of knowledge and experience, school administrative problems, lack of training, and reliance on assessment preference are faced. Based on the findings, the study concludes with recommendations that can be implemented to develop assessment for learning strategies in the language classrooms; to minimize the challenges faced by Amharic language teachers in Ethiopian general education (1-12) schools.
29
Rose, Sharon, and Wolf Leslau. "Reference Grammar of Amharic." Language 72, no. 4 (December 1996): 886. http://dx.doi.org/10.2307/416150.
Full text
30
Nosnitsin, Denis, and Maria Bulakh. "“Behold, I have written it on parchment…” Two Early Amharic Poems from Ms. Ef. 10 (Koriander 2), St. Petersburg." Afrika und Übersee 93 (December 31, 2020): 239–56. http://dx.doi.org/10.15460/auue.2020.93.1.214.
Full textAbstract:
The article deals with two short poems in Amharic from Ms. Ef. 10 kept in the Library of the Institute of Oriental Manuscripts of the Russian Academy of Sciences, St. Petersburg. Amharic, a Semitic language of Ethiopia, came to function as the second written language of Ethiopian Empire in the course of the 19th century. Samples of Amharic texts prior to this period are scanty and worthy of special study. The poems in question can be dated to the period end of the 17th – beginning of the 18th century. The article provides the texts of the poems with translation and linguistic and philological commentary, accompanied by a short description of Ms. Ef. 10.
31
Dikken, Marcel den. "Amharic Relatives and Possessives: Definiteness, Agreement, and the Linker." Linguistic Inquiry 38, no. 2 (March 2007): 302–20. http://dx.doi.org/10.1162/ling.2007.38.2.302.
Full textAbstract:
Ouhalla's (2004) valuable discussion of relativized and possessed noun phrases in Amharic leaves a number of questions open. Foremost among these is the placement of the linker element yä-. Starting from an analysis of relative clauses and possessors as predicates of their “heads,” this article develops a syntax of complex noun phrases in Amharic that explains the raison d'être and placement of yä-, and also accommodates facts about definiteness marking and agreement in the Amharic complex noun phrase that have hitherto largely escaped attention or analysis. The analysis emphasizes the role of Predicate Inversion and head movement in syntax, and it confirms and extends the minimalist Agree- and phase-based approach to syntactic relationships.
32
Endalie, Demeke, Getamesay Haile, and Wondmagegn Taye. "Bi-directional long short term memory-gated recurrent unit model for Amharic next word prediction." PLOS ONE 17, no. 8 (August 18, 2022): e0273156. http://dx.doi.org/10.1371/journal.pone.0273156.
Full textAbstract:
The next word prediction is useful for the users and helps them to write more accurately and quickly. Next word prediction is vital for the Amharic Language since different characters can be written by pressing the same consonants along with different vowels, combinations of vowels, and special keys. As a result, we present a Bi-directional Long Short Term-Gated Recurrent Unit (BLST-GRU) network model for the prediction of the next word for the Amharic Language. We evaluate the proposed network model with 63,300 Amharic sentence and produces 78.6% accuracy. In addition, we have compared the proposed model with state-of-the-art models such as LSTM, GRU, and BLSTM. The experimental result shows, that the proposed network model produces a promising result.
33
Gebreyohanns, Mehari, Chiamaka C. Onuigbo, Azhar Ali, Sonja E. Stutzman, and DaiWai M. Olson. "Providing Stroke and Hypertension Education in Amharic for Ethiopian Persons Living in Dallas, Texas, United States." Creative Nursing 26, no. 1 (February 1, 2020): 66–73. http://dx.doi.org/10.1891/1078-4535.26.1.66.
Full textAbstract:
BackgroundThe purpose of this study was to compare knowledge of a stroke education module provided to bilingual members of the Ethiopian immigrant population in Dallas, Texas, presented in the Amharic language as compared to in English.MethodsA convenience sample of 84 participants were recruited using a snowball technique and randomly assigned to receive education in English or Amharic. The participants completed a pre- and posttest of their knowledge about strokes, a demographic survey, and a satisfaction survey. Data was analyzed using a general linear model and chi-square analysis.ResultsThere were no statistically significant differences between satisfaction scores comparing those educated in Amharic versus English (χ2 = 6.5108, p = .0107). Although mean pretest (10.8) and posttest (16.4) stroke knowledge scores were higher across all groups (p < .001), the mean posttest scores were lower for subjects who watched the Amharic versus the English video (14.9 vs. 18.1, p = .003).ConclusionThis study did not show a statistically significant increase in knowledge about stroke when presented learning materials in subjects' native language compared to in English. The use of video to present stroke and stroke-risk educational content can be used in future research and global health initiatives to increase stroke knowledge in the Amharic-speaking community.
34
Teferra, Solomon, Martha Yifiru, and Tanja Schultz. "DNN-based Multilingual Acoustic Modeling for Four Ethiopian Languages." SINET: Ethiopian Journal of Science 46, no. 3 (March 27, 2024): 237–49. http://dx.doi.org/10.4314/sinet.v46i3.2.
Full textAbstract:
In this paper, we present the results of experiments conducted on multilingual acoustic modeling in the development of an Automatic Speech Recognition (ASR) system using speech data of phonetically much related Ethiopian languages (Amharic, Tigrigna, Oromo and Wolaytta) with multilingual (ML) mix and multitask approaches. The use of speech data from only phonetically much related languages brought improvement over results reported in a previous work that used 26 languages (including the four languages). A maximum Word Error Rate (WER) reduction from 25.03% (in the previous work) to 21.52% has been achieved for Wolaytta, which is a relative WER reduction of 14.02%. As a result of using multilingual acoustic modeling for the development of an automatic speech recognition (ASR) system, a relative WER reduction of up to 7.36% (a WER reduction from 23.23% to 21.52%) has been achieved over a monolingual ASR. Compared to the ML mix, the multitask approach brought a better performance improvement (a relative WERs reduction of up to 5.9%). Experiments have also been conducted using Amharic and Tigrigna in a pair and Oromo and Wolaytta in another pair. The results of the experiments showed that languages with a relatively better language resources for lexical and language modeling (Amharic and Tigrigna) benefited from the use of speech data from only two languages. Generally, the findings show that the use of speech corpora of phonetically related languages with the multitask multilingual modeling approach for the development of ASR systems for less-resourced languages is a promising solution.
35
Vatvedt Fjeld, Ruth E., Elsa Kristiansen, Marianne Rathje, Veturlidi Oskarsson, Natalia Konstaninovskaia, Inayat Gill, and Fekede Menuta. "The worldwide use and meaning of the f-word." Intercultural Pragmatics 16, no. 1 (March 5, 2019): 85–111. http://dx.doi.org/10.1515/ip-2019-0004.
Full textAbstract:
Abstract This article documents the increasing use of the English curse word fuck worldwide, as well as its degree of adaption into the host language, its syntactic function, and its meaning and its strength as taboo. Comparing the use of fuck with a special focus on the Nordic countries (Norway, Denmark, and Iceland) with its use in Eurasia and Africa (with different alphabets, namely Cyrillic in Russia, Devanāgarī in India and Ge’ez script in Ethiopia), we found some similar developmental patterns, but also differences, for example to what degree the English loan word has replaced local curses and in what ways among social groups within a country. Comparing the terms used for the same concept was challenging because some countries have better text corpora and more research on written languages and especially on taboos, and those without such resources required additional minor investigations for a baseline. Findings revealed that fuck has spread worldwide from English, and it is commonly used in Nordic languages today. In Russian fuck is also adopted into the heritage language to a relatively high degree, and it has further gained importance in the vocabulary of India, where English has become the most used language by the higher and middle classes, but less so by lower classes. In contrast, the study of Amharic language in Ethiopia shows that the f-word is rarely used at all, and only by youngsters. We found a pattern starting from the outer North with Icelandic having adapted and adopted the word fuck the most, a slight decline in use in Norwegian and Danish, with less adaption and use in Russian, even less in Indian-English or Hindi, and being more or less absent in the African language Amharic. Formally though it is used conceptually both in Hindi and Amharic.
36
Alqarni, Muteb. "Arabic loanwords in seven Ethiopian languages." Brill’s Journal of Afroasiatic Languages and Linguistics 13, no. 2 (November 29, 2021): 423–75. http://dx.doi.org/10.1163/18776930-01302009.
Full textAbstract:
Abstract Within the Theory of Constraints and Repair Strategies (Paradis, 1988a,b; Paradis & LaCharité, 1993, 1997, 2001, 2002, 2005, 2008, henceforth TCRS), we provide a formal analysis to the Arabic loanwords in seven languages spoken in Ethiopia: Ge’ez, Tigre, Tigrinya, Amharic, Harari, Argobba and Gurage. The analysis draws upon a corpus of 540 loanwords extracted from the works of Leslau (1956a,b,c; 1957a,b,c; 1958; 1963; 1990). The article presents theoretical challenges to the TCRS Loanword Model (Paradis & LaCharité, 1997), in particular to the Threshold Principle which stipulates that an illicit segment should universally undergo less than two repairs to be licensed in the borrowing language; beyond this limit, it will be deleted. The adaptations of Arabic segmental malformations in these seven Ethiopian languages, however, exceed this number totaling in certain cases to six repairs. The article also discusses the Arabic gutturals, [ʔ], [ʕ] and [ħ], which undergo unpredictable deletion in Amharic and Argobba, showing that the Non-Availability Hypothesis (Paradis & LaCharité, 2001) cannot account for these deletions either. Although the Francophones systematically delete gutturals in Arabic loanwords due to the non-availability of Pharyngeal node in French, the inventories of Amharic and Argobba include the laryngeal [h], the uvular [q] and the glottalized ejectives, thus employing Pharyngeal node plus the features [RTR] and [constricted glottis] as phonologically treatable primitives.
37
Asaye, Gashaw Arutie. "Static locative expressions in Amharic." Journal of African Languages and Linguistics 42, no. 1 (May 1, 2021): 1–26. http://dx.doi.org/10.1515/jall-2021-2017.
Full textAbstract:
Abstract This paper describes the semantics of static locative expressions in Amharic, particularly the variety spoken in Godʒdʒam. The analysis shows that the semantic category of a site subsumed under Path is exclusively expressed by an adposition. The adpositions can be specific and general locatives. The specific locatives show a specific type of topological relation (for instance, verticality as in tatʃtʃ ‘below, under,’ horizontality as in fit ‘front,’ containment as in wɨst’ ‘in’) between figure and ground entities, but not the general locatives. Besides, static positional verbs encode the conflation of the fact of locatedness with a manner of the positioning of a figure. Based on Talmy’s Motion event typology, the present study has identified that Amharic uses a satellite-framed pattern in static locative constructions exclusively. Moreover, based on Ameka & Levinson’s typology of locative predication, Amharic can be classified under type Ia where a language uses a dummy verb in basic locative construction.
38
Asaye, Gashaw Arutie. "Static locative expressions in Amharic." Journal of African Languages and Linguistics 42, no. 1 (May 1, 2021): 1–26. http://dx.doi.org/10.1515/jall-2021-2017.
Full textAbstract:
Abstract This paper describes the semantics of static locative expressions in Amharic, particularly the variety spoken in Godʒdʒam. The analysis shows that the semantic category of a site subsumed under Path is exclusively expressed by an adposition. The adpositions can be specific and general locatives. The specific locatives show a specific type of topological relation (for instance, verticality as in tatʃtʃ ‘below, under,’ horizontality as in fit ‘front,’ containment as in wɨst’ ‘in’) between figure and ground entities, but not the general locatives. Besides, static positional verbs encode the conflation of the fact of locatedness with a manner of the positioning of a figure. Based on Talmy’s Motion event typology, the present study has identified that Amharic uses a satellite-framed pattern in static locative constructions exclusively. Moreover, based on Ameka & Levinson’s typology of locative predication, Amharic can be classified under type Ia where a language uses a dummy verb in basic locative construction.
39
Gashaw, Anegagregn. "Rhythm in Ethiopian English: Implications for the Teaching of English Prosody." International Journal of Education and Literacy Studies 5, no. 1 (January 31, 2017): 13. http://dx.doi.org/10.7575/aiac.ijels.v.5n.1p.13.
Full textAbstract:
In order to verify that English speeches produced by Ethiopian speakers fall under syllable-timed or stress-timed rhythm, the study tried to examine the nature of stress and rhythm in the pronunciation of Ethiopian speakers of English by focusing on one language group speaking Amharic as a native language. Using acoustic analysis of the speeches recorded from four Amharic speaking learners and two Canadian native speakers of English, comparison was made between pitch contours and length of speeches between speech samples of Amharic speakers with native speakers who are used in this study as a point of reference. The result of acoustic analysis showed that Amharic native samples displayed actual peaks on almost all words, taking longer time of articulation. It can be said that acoustic measures the study used for prosodic assessment of Ethiopian English exemplified the most occurring production tendencies of pronunciation that learners should give attention to. English pronunciation teaching to Ethiopians should involve the practice of stressing, un-stressing and rhythm to help learners improve their pronunciation from the influence of the syllable-timed rhythm of their mother tongue.
40
Brhanemeskel, Getnet Mezgebu, Solomon Teferra Abate, Tewodros Alemu Ayall, and Abegaz Mohammed Seid. "Amharic Speech Search Using Text Word Query Based on Automatic Sentence-like Segmentation." Applied Sciences 12, no. 22 (November 18, 2022): 11727. http://dx.doi.org/10.3390/app122211727.
Full textAbstract:
More than 7000 languages are spoken in the world today. Amharic is one of the languages spoken in the East African country Ethiopia. A lot of speech data is being made every day in different languages as machines are getting better at processing and have improved storing capacity. However, searching for a particular word with its respective time frame inside a given audio file is a challenge. Since Amharic has its own distinguishing characteristics, such as glottal, palatal, and labialized consonants, it is not possible to directly use models that are developed for other languages. A popular approach in developing systems for searching particular information in speech involves using an automatic speech recognition (ASR) module that generates the text version of the speech where the word or phrase is searched based on text query. However, it is not possible to transcribe a long audio file without segmentation, which in turn affects the performance of the ASR module. In this paper, we are reporting our investigation on the effects of manual and automatic speech segmentation of Amharic audio files in a spiritual domain. We have used manual segmentation as a baseline for our investigation and found out that sentence-like automatic segmentation resulted in a word error rate (WER) closer to the WER achieved on the manually segmented test speech. Based on the experimental results, we propose Amharic speech search using text word query (ASSTWQ) based on automatic sentence-like segmentation. Since we have achieved lower WER using the previously developed speech corpus, which is in a broadcast news domain, together with the in-domain speech corpus, we recommend using both in- and out-domain speech corpora to develop the Amharic ASR module. The performance of the proposed ASR is a WER of 53% that needs further improvement. Combining two language models (LMs) developed using training text from the two different domains (spiritual and broadcast news) allowed a WER reduction from 53% to 46%. Therefore, we have developed two ASSTWQ systems using the two ASR modules with WERs of 53% and 46%.
41
Et. al., Gizachew Belayneh Gebre. "Artificial Neural Network Based Amharic Language Speaker Recognition." Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 3 (April 11, 2021): 5105–16. http://dx.doi.org/10.17762/turcomat.v12i3.2043.
Full textAbstract:
In this artificial intelligence time, speaker recognition is the most useful biometric recognition technique. Security is a big issue that needs careful attention because of every activities have been becoming automated and internet based. For security purpose, unique features of authorized user are highly needed. Voice is one of the wonderful unique biometric features. So, developing speaker recognition based on scientific research is the most concerned issue. Nowadays, criminal activities are increasing day to day in different clever way. So, every country should have strengthen forensic investigation using such technologies. The study was done by inspiration of contextualizing this concept for our country. In this study, text-independent Amharic language speaker recognition model was developed using Mel-Frequency Cepstral Coefficients to extract features from preprocessed speech signals and Artificial Neural Network to model the feature vector obtained from the Mel-Frequency Cepstral Coefficients and to classify objects while testing. The researcher used 20 sampled speeches of 10 each speaker (total of 200 speech samples) for training and testing separately. By setting the number of hidden neurons to 15, 20, and 25, three different models have been developed and evaluated for accuracy. The fourth-generation high-level programming language and interactive environment MATLAB is used to conduct the overall study implementations. At the end, very promising findings have been obtained. The study achieved better performance than other related researches which used Vector Quantization and Gaussian Mixture Model modelling techniques. Implementable result could obtain for the future by increasing number of speakers and speech samples and including the four Amharic accents.
42
Böll, Verena, and Getie Gelaye. "David Appleyard: Colloquial Amharic: A Complete Language Course." Aethiopica 1 (September 13, 2013): 229–31. http://dx.doi.org/10.15460/aethiopica.1.1.622.
Full text
43
Tesfagergish, Senait Gebremichael, Robertas Damasevicius, and Jurgita Kapociūtė-Dzikienė. "Deep learning-based sentiment classification in Amharic using multi-lingual datasets." Computer Science and Information Systems, no. 00 (2023): 42. http://dx.doi.org/10.2298/csis230115042t.
Full textAbstract:
The analysis of emotions expressed in natural language text, also known as sentiment analysis, is a key application of natural language processing (NLP). It involves assigning a positive, negative (sometimes also neutral) value to opinions expressed in various contexts such as social media, news, blogs, etc. Despite its importance, sentiment analysis for under-researched languages like Amharic has not received much attention in NLP yet due to the scarcity of resources required to train such methods. This paper examines various deep learning methods such as CNN, LSTM, FFNN, BiLSTM, and transformers, as well as memory-based methods like cosine similarity, to perform sentiment classification using the word or sentence embedding techniques. This research includes training and comparing mono-lingual or cross-lingual models using social media messages in Amharic on Twitter. The study concludes that the lack of training data in the target language is not a significant issue since the training data 1) can be machine translated from other languages using machine translation as a data augmentation technique [33], or 2) cross-lingual models can capture the semantics of the target language, even when trained on another language (e.g., English). Finally, the FFNN classifier, which combined the sentence transformer and the cosine similarity method, proved to be the best option for both 3-class and 2-class sentiment classification tasks, achieving 62.0% and 82.2% accuracy, respectively.
44
Mekonnen, Habtamu Sewunet, Helena Lindgren, Biftu Geda, Telake Azale, and Kerstin Erlandsson. "Translation, Cultural Adaptation, and Psychometric Properties of the Life Satisfaction Index for the Third Age—Short Form (LSITA-SF12) for Use among Ethiopian Elders." Nursing Reports 11, no. 4 (December 7, 2021): 981–96. http://dx.doi.org/10.3390/nursrep11040089.
Full textAbstract:
(1) Background: Self-reported measures play a crucial role in research, clinical practice, and health assessment. Instruments used to assess life satisfaction need validation to ensure that they measure what they are intended to detect true variations over time. An adapted instrument measuring life satisfaction for use among Ethiopian elders was lacking; therefore, this study aimed to culturally adapt and evaluate the psychometric properties of the Life Satisfaction Index for the Third Age—Short Form (LSITA-SF12) in Ethiopia. (2) Methods: Elderly people (n = 130) in Metropolitan cities of northwestern Ethiopia answered the LSITA-SF12 in the Amharic language. Selected reliability and validity tests were examined. (3) Result: The scale had an acceptable limit of content validity index, internal consistency, test-retest, inter-rater reliabilities, and concurrent and discriminant validities. (4) Conclusion: The Amharic language version of LSITA-SF12 appeared to be valid and reliable measures and can be recommended for use in research and clinical purposes among Amharic-speaking Ethiopian elders.
45
Baker, Mark C. "On the Relationship of Object Agreement and Accusative Case: Evidence from Amharic." Linguistic Inquiry 43, no. 2 (January 2012): 255–74. http://dx.doi.org/10.1162/ling_a_00085.
Full textAbstract:
This article shows that accusative case and object agreement are not closely related in Amharic, a language in which both are morphologically overt. This suggests that it is wrong to generalize Chomsky’s claim that agreement and case are both manifestations of the same Agree relation from subjects to objects across the board. I show that object agreements in Amharic are the true manifestations of Agree (not pronominal clitics), whereas accusative case is assigned independently, to the lower of two nominals in the same domain. The relationship between case and agreement can thus vary parametrically.
46
TACHBELIE, MARTHA YIFIRU, SOLOMON TEFERRA ABATE, and WOLFGANG MENZEL. "Using morphemes in language modeling and automatic speech recognition of Amharic." Natural Language Engineering 20, no. 2 (December 12, 2012): 235–59. http://dx.doi.org/10.1017/s1351324912000356.
Full textAbstract:
AbstractThis paper presents morpheme-based language models developed for Amharic (a morphologically rich Semitic language) and their application to a speech recognition task. A substantial reduction in the out of vocabulary rate has been observed as a result of using subwords or morphemes. Thus a severe problem of morphologically rich languages has been addressed. Moreover, lower perplexity values have been obtained with morpheme-based language models than with word-based models. However, when comparing the quality based on the probability assigned to the test sets, word-based models seem to fare better. We have studied the utility of morpheme-based language models in speech recognition systems and found that the performance of a relatively small vocabulary (5k) speech recognition system improved significantly as a result of using morphemes as language modeling and dictionary units. However, as the size of the vocabulary increases (20k or more) the morpheme-based systems suffer from acoustic confusability and did not achieve a significant improvement over a word-based system with an equivalent vocabulary size even with the use of higher order (quadrogram) n-gram language models.
47
Miftah, Mohammed. "Analysis of Morphological Shifts Gender and Number Shift Observed in the Translation of the Holy Qur’aan from Arabic into Amharic." International Journal of Social Sciences 6, no. 24 (February 20, 2022): 36–59. http://dx.doi.org/10.52096/usbd.6.24.3.
Full textAbstract:
Abstract In this article, morphological shifts, number and gender shits observed in the translation of the Holy Qur’aan from Arabic into Amharic have been discussed and analyzed. Shifts in agreement in number and gender between parts of a sentence have been discussed. From the discussion given in the article one can conclude that agreement in number and gender is sensitive to word order in Arabic. For example, when the subject follows the verb the suffixes that show agreement are absent, but they are obligatorily present if the subject precedes the verb. Therefore, sometimes agreement in number and gender may not be strict in Arabic. However, in Amharic there should always be strict agreement in gender and number. Therefore shifts in number and gender have been obligatorily made by the translators of the Holy Qur’aan from Arabic into Amharic to produce grammatical sentences in the target language structure. However, in some instances, as discussed in the article, the translators closely adhered to the source language structure which produced ungrammatical or unknown structures in the target language structure. This may make some structures in the target text incomprehensible. Key Words: Source text, target text, target language structure, morphological shifts, gender and number Shift
48
Muhye, Ahmed, and Netsanet Fentahun. "Validation of Quality-of-Life assessment tool for Ethiopian old age people." F1000Research 12 (March 14, 2023): 282. http://dx.doi.org/10.12688/f1000research.130379.1.
Full textAbstract:
Background: A valid and reliable quality of life (QOL) assessment tool is critical for identifying health issues, evaluating health interventions, and establishing the best health policies and care plans. One of the tools for this goal is the World Health Organization's Quality of Life Old module (WHOQOL-OLD). It is validated and available in more than 20 languages globally, except Amharic (the widely spoken language in Ethiopia). As a result, the purpose of this study was to translate it into Amharic language and validate it among the elderly people in Bahir Dar City, Northwestern Ethiopia. Methods: This was a cross-sectional study conducted among 180 community-dwelling old age people in Bahir Dar City, Ethiopia, from January 16 to March 13, 2021. Psychometric validation was achieved through Cronbach’s alpha of the internal consistency reliability test and construct validity from confirmatory factor analysis. Results: The study participants were aged between 60 and 90 years, with a mean age of 69.44. Females made up 61.7% of the study population, and 40% of them could not read or write. The results showed a relatively low level of quality of life, with a total transformed score of 58.58±23.15. The Amharic version of the WHOQOL-OLD showed a Cronbach’s Alpha value of 0.96 and corrected item-total correlations of more than 0.74. The confirmatory factor analysis confirmed the six-domain model with a chi-square (X2) of 341.98 and a p-value less than 0.001. The comparative fit index (CFI) was 0.98, Tucker-Lewis’s index (TCL) was 0.97, and the root mean square error of approximation (RMSEA) was 0.046. Conclusion: The Amharic version of the WHOQOL-OLD indicated good internal consistency reliability and construct validity. The tool can be utilized to provide care to Ethiopian community-dwelling old age people.
49
Muhye, Ahmed, and Netsanet Fentahun. "Validation of Quality-of-Life assessment tool for Ethiopian old age people." F1000Research 12 (March 28, 2024): 282. http://dx.doi.org/10.12688/f1000research.130379.2.
Full textAbstract:
Background A valid and reliable quality of life (QOL) assessment tool is critical for identifying health issues, evaluating health interventions, and establishing the best health policies and care plans. One of the tools for this goal is the World Health Organization's Quality of Life Old module (WHOQOL-OLD). It is validated and available in more than 20 languages globally, except Amharic (the widely spoken language in Ethiopia). As a result, the purpose of this study was to translate it into Amharic language and validate it among the elderly people in Bahir Dar City, Northwestern Ethiopia. Methods This was a cross-sectional study conducted among 180 community-dwelling old age people in Bahir Dar City, Ethiopia, from January 16 to March 13, 2021. Psychometric validation was achieved through Cronbach’s alpha of the internal consistency reliability test and construct validity from confirmatory factor analysis. Results The study participants were aged between 60 and 90 years, with a mean age of 69.44. Females made up 61.7% of the study population, and 40% of them could not read or write. The results showed a relatively low level of quality of life, with a total transformed score of 58.58±23.15. The Amharic version of the WHOQOL-OLD showed a Cronbach’s Alpha value of 0.96 and corrected item-total correlations of more than 0.74. The confirmatory factor analysis confirmed the six-domain model with a chi-square (X2) of 341.98 and a p-value less than 0.001. The comparative fit index (CFI) was 0.98, Tucker-Lewis’s index (TCL) was 0.97, and the root mean square error of approximation (RMSEA) was 0.046. Conclusion The Amharic version of the WHOQOL-OLD indicated good internal consistency reliability and construct validity. The tool can be utilized to provide care to Ethiopian community-dwelling old age people.
50
Gelagay, Almaz Wasse. "Lexical Translanguaging in Textbook Preparation for Education in the Gamo Language of Ethiopia." Languages 8, no. 3 (June 26, 2023): 154. http://dx.doi.org/10.3390/languages8030154.
Full textAbstract:
As a country where more than 85 languages are spoken, Ethiopia framed, in its Education and Training Policy of 1994, which was revised in 2021, the right to use mother tongue in primary education. Following this, around 33 languages are implemented in schools as a Medium of Instruction (MoI). Gamo is one of the languages used as a MoI in primary education and taught as a subject up to high school. This functional expansion of Gamo into Education required textbook preparation, and accordingly, textbooks for different subjects, including Gamo as a language subject, were published. One major feature of the Gamo textbooks is availability of Amharic and English words, and this research aims to apply translanguaging, which is the discursive language practices of bilingual speakers to describe the practice of using words from different languages in the textbooks. Lexical data were collected from five textbooks written in Gamo and interviews were held with students and teachers to find out information about the process of textbook writing and translanguaging. The strategies identified in the textbooks include alternative translanguaging, borrowing, lexical inventions and bilingual compounds. These strategies were used to address education in the Gamo language and to communicate meaning effectively. Writers used their Amharic and English repertoire to represent meaning when a word for a concept is not available in Gamo. In other instances, alternative words were provided as a means of enhancing meaning clarity.