Journal articles: 'Marathi language'

1

Chaitrali B. Kamble and Kishor T. Mane. "A Review on Handwritten Recognition System Using Machine Learning Techniques." International Research Journal on Advanced Engineering Hub (IRJAEH) 2, no. 06 (June 7, 2024): 1590–99. http://dx.doi.org/10.47392/irjaeh.2024.0218.

Full text

Abstract:

Marathi language is the most widely spoken language in India, and its script is unique and complex Handwriting recognition of the Marathi language poses a significant challenge due to the variety in writing styles and the script's complexity. Machine learning techniques can help in building Marathi handwriting recognition systems that can accurately recognize handwritten Marathi text. The Devanagari script is the source of Marathi, the official language of Maharashtra. Devanagari script is used for the Marathi language and it has 12 vowels and 36 consonants. Handwritten character recognition in any script is a challenging task for researchers. Nowadays, handwritten Marathi character identification is the hardest problem. Sharing physical documents is a laborious and time-consuming task. Because of the structure, shape, various strokes, and writing styles, handwritten Marathi characters are more difficult to read as well as understand. Marathi handwritten recognition system is very essential in various aspects as further described. Preservation of cultural heritage. The mechanism of recognition facilitates accessibility by making Marathi information more easily accessible to people who are visually impaired or have difficulty with traditional text input techniques. The paper focuses on a review of methods used for the development of handwritten character recognition systems using machine learning approaches, including Sanskrit, Hindi, Marathi, and Maithili languages. Different machine learning classifiers such as Decision Tree, Nearest Centroid, KNN, Extra Trees, and Random Forest were implemented and compared for their performance. Extra Trees and Random Forest showed better accuracy.

APA, Harvard, Vancouver, ISO, and other styles

2

Lokhande, Kalyani, and Dhanashree Tayade. "English-Marathi Cross Language Information Retrieval System." International Journal of Advanced Research in Computer Science and Software Engineering 7, no. 8 (August 30, 2017): 112. http://dx.doi.org/10.23956/ijarcsse.v7i8.34.

Full text

Abstract:

Nowadays, diﬀerent types of content in diﬀerent languages are available on World Wide Web and their usage is increasing rapidly. Cross Language Information Retrieval (CLIR) deals with retrieval of documents in another language than the language of the requested query. Various researchers worked on Cross Language Information Retrieval systems for Indian languages using diﬀerent translation approaches. There is still CLIR system to be developed which allow user to retrieve Marathi documents when English query is given. In the proposed English to Marathi Cross Language Information Retrieval system, translation is based on query translation approach. The proposed system retrieves Marathi documents depending on matching terms in query. The performance of the proposed system is improved by query pre-processing and query expansion using WordNet.

APA, Harvard, Vancouver, ISO, and other styles

3

Shirkande, Aparna, and Alok Agarwal. "A Review on Various MODI Text Recognition Techniques." Journal of Image Processing and Artificial Intelligence 9, no. 1 (January 4, 2023): 1–7. http://dx.doi.org/10.46610/joipai.2023.v09i01.001.

Full text

Abstract:

MODI script is an ancient language of the Marathi people. MODI script is used to write the Marathi language, which is the mother language of Maharashtra, India. To understand this ancient language here we analyze text recognition techniques. MODI script was used primarily by administrative people to keep their accounts, as well as most of the revenue documents, were written in MODI language. For recognition of such text, number of image processing techniques are used. The official scriptures of Goa were previously written in this 17th-century Balbodh style of Devanagari, which is currently being restored. It is now a practical visual reminder of the former Maratha era and a specialized research skill; it is a technological key required primarily to access the Maratha state's empirical history through these archive resources. This paper explains the previous analysis of MODI text recognition. MODI text recognition system is well explained with the help of a generalized text recognition system model. The model includes image acquisition, normalization, binarization, segmentation, feature extraction, training, and classification lastly recognized image. Numerous optional strategies that have been used in various identification systems are available for each level. The history of the Maratha dynasty and other significant facts can be revealed in numerous MODI manuscripts by using these different techniques to identify MODI characters. Also, some applications of text recognition are explained in this paper.

APA, Harvard, Vancouver, ISO, and other styles

4

Sule, A. "Communicating through Vernacular Media: Scope and Challenges." Proceedings of the International Astronomical Union 10, H16 (August 2012): 652–53. http://dx.doi.org/10.1017/s1743921314012733.

Full text

Abstract:

India is a country with a large number of languages which not only differ in scripts but are essentially part of different language families. “Marathi“ is one such Indian regional language spoken by nearly 70 million people and is the native language of the author. Like all major regional languages, there is a strong and vibrant media in Marathi with 45 odd newspapers and 6 television news channels.

APA, Harvard, Vancouver, ISO, and other styles

5

Doibale, Pradyumna, Suryakant Deogade, Arun Khalikar, Sattyam Wankhede, Archit Kapadia, and Vinay Dutta. "Translation and Validation of Marathi Version of Oral Health Impact Profile?14, a Measure of Oral Health?Related Quality of Life." Indian Journal of Community Health 34, no. 1 (March 31, 2022): 101–5. http://dx.doi.org/10.47203/ijch.2022.v34i01.019.

Full text

Abstract:

Background: A quality of life (QoL) assessment tool needs to be translated and validated in the language of the participants to whom it is administered. Therefore, the oral health impact profile-14 (OHIP-14) scale, developed originally in English, has been translated into different languages like Hindi, Gujrati, etc. The Marathi version of OHIP-14 will be useful to assess in regions where the Marathi language is prominently spoken. Thus, the present study was carried out to translate and validate the Marathi version of the OHIP-14 instrument to measure the oral health-related quality of life. Aims & Objectives: To translate and validate the English Version of the OHIP-14 instrument in the Marathi Language. Materials and Methods: This was a descriptive cross-sectional study in which 128 participants were selected through a convenient sampling method. The English version of the OHIP-14 was translated using the forward-backward translation technique, and participants were given English and the Marathi versions of the OHIP-14 questionnaire. The filled questionnaires were subjected to statistical analysis. Result: The difference in mean scores was not statistically significant(p=0.828). Pearson’s correlation coefficient test was 0.999, suggesting that the translated Marathi version is highly correlated with the original English version. Conclusion: The Marathi version of OHIP-14 is a valid, and reliable instrument for assessing QoL among the population who speak Marathi.

APA, Harvard, Vancouver, ISO, and other styles

6

Deshpande, Prachi. "The Marathi Kaulnāmā: Property, Sovereignty and Documentation in a Persianate Form." Journal of the Economic and Social History of the Orient 64, no. 5-6 (November 26, 2021): 583–614. http://dx.doi.org/10.1163/15685209-12341547.

Full text

Abstract:

Abstract Kaulnāmās were ubiquitous in early modern Marathi bureaucratic documentation. They were issued as deeds of assurance offering protection and confirming various rights, especially during warfare or invasion. Such documents were issued at different levels of the administrative hierarchy in the Adilshahi and Maratha administrations to prevent flight from troubled areas, extend cultivation, and encourage commerce. They also recorded grants of waste land to cultivators on graduated rates of taxation, or to merchants for developing market towns. This paper historicizes the kaulnāmā form from the seventeenth through the early nineteenth centuries, exploring the kinds of transactions of power, sovereignty and property it was part of. Through this focus on the trajectory of particular documentary forms, it reflects on the nature of the Persianate within Marathi bureaucratic practices, and the history of the Marathi language more broadly.

APA, Harvard, Vancouver, ISO, and other styles

7

Joshi, Prof Indira. "Video Summarization for Marathi Language." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 05 (May 3, 2024): 1–5. http://dx.doi.org/10.55041/ijsrem32024.

Full text

Abstract:

The Video Summarization Platform using Python Flask is a comprehensive tool designed to summarize Marathi and English videos while providing summaries in Hindi, Marathi, and English languages. Leveraging machine learning and natural language processing (NLP) techniques, this platform offers a sophisticated solution for efficiently extracting key information from videos. The platform begins by transcribing the audio content of the video into text using automatic speech recognition (ASR) technology. This transcription process ensures that the platform can accurately analyze and summarize the video's content. Next, the text is translated into the target languages, namely Hindi, Marathi, and English, enabling users from diverse linguistic backgrounds to access the summarized content. To generate concise and informative summaries, advanced NLP algorithm is applied. This algorithm analyze the transcribed text to identify the most significant phrases, sentences, and concepts. By considering factors such as keyword frequency, semantic relevance, and context, the platform effectively distils the video's content into digestible summaries. Additionally, machine learning models are employed to classify the type of video content. These models are trained on diverse datasets encompassing various video genres and topics. By recognizing patterns and features within the video content, the platform can accurately categorize videos into distinct types, such as news, interviews, tutorials, or entertainment. The platform's user interface, powered by Python Flask, offers a seamless experience for users to upload videos, select their preferred language for summarization, and receive concise summaries in their chosen languages. The intuitive design ensures accessibility and ease of use, catering to both novice and advanced users. Overall, the Video Summarization Platform serves as a valuable resource for individuals seeking efficient ways to consume multimedia content. Whether for educational, informational, or entertainment purposes, this platform empowers users to access summarized video content in multiple languages, facilitated by cutting-edge machine learning and NLP technologies. Key Words: Transcription, Marathi-speaking users, Marathi YouTube videos, video content, transcription, summary, translation, Natural Language Toolkit (NLTK), content comprehension, user interaction data, past summaries, recommendation

APA, Harvard, Vancouver, ISO, and other styles

8

Mulla, Rahesha, and B. Suresh Kumar. "Text-Independent Automatic Dialect Recognition of Marathi Language using Spectro-Temporal Characteristics of Voice." International Journal on Recent and Innovation Trends in Computing and Communication 10, no. 2s (December 31, 2022): 313–21. http://dx.doi.org/10.17762/ijritcc.v10i2s.5949.

Full text

Abstract:

Text-independent dialect recognition system is proposed in this paper for Marathi language. India is rich in language varieties. Each language in turn has its unique dialect variations. Maharashtra has Marathi as official language and for Goa it is a co-official language . In literature there are very few studies available for Indian language recognition and then their respective dialect recognition. So research work available for regional languages such as Marathi is extremely limited. As a part of research work, an attempt is made to generate a case study of a low resourced Marathi language dialect recognition system. The study was carried out using Marathi speech data corpus provided by Linguistic Data Consortium for Indian Language (LDC- IL). This corpus includes four major dialects of Marathi speakers. The efficiency and performance evaluation of the explored spectral (rhythmic) and temporal features are carried out to perform classification tasks. We investigated the performance of six different classifiers; K-nearest neighbor (KNN), Naïve Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT) classifier , Stochastic Gradient Descent (SGD) classifier and Ridge Classifier (RC). Experimental results have demonstrated that the RC classifier worked well with 84.24% of accuracy for fifteen spectral and temporal features. With twelve MFCCs it has been observed that SGD has outperformed among all classifiers with accuracy of 80.63%. For further study, a prominent feature subset as a part of dimensionality reduction has been identified using chi square, mutual information and ANOVA-f test. In this chi-square based feature extraction method has proven to be the best over over mutual information and ANOVA f-test.

APA, Harvard, Vancouver, ISO, and other styles

9

Nikam, Saurabh Ravindra. "Character Segmentation and Recognition of Marathi Language." International Journal for Research in Applied Science and Engineering Technology 9, no. 12 (December 31, 2021): 1544–51. http://dx.doi.org/10.22214/ijraset.2021.39566.

Full text

Abstract:

Abstract: In this paper Segmentation is one the most important process which decides the success of character recognition fashion. Segmentation is used to putrefy an image of a sequence of characters into sub images of individual symbols by segmenting lines and words. In segmentation image is partitioned into multiple corridor. With respect to the segmentation of handwritten words into characters it's a critical task because of complexity of structural features and kinds in writing styles. Due to this without segmentation these touching characters, it's delicate to fete the individual characters, hence arises the need for segmentation of touching characters in a word. Then we consider Marathi words and Marathi Numbers for segmentation. The algorithm is use for Segmentation of lines and also characters. The segmented characters are also stores in result variable. First it Separate the lines and also it Separate the characters from the input image. This procedure is repeated till end of train. Keywords: Image Segmentation, Handwritten Marathi Characters, Marathi Numbers, OCR.

APA, Harvard, Vancouver, ISO, and other styles

10

Mahender, C. Namrata, Ramesh Ram Naik, and Maheshkumar Bhujangrao Landge. "Author Identification for Marathi Language." Advances in Science, Technology and Engineering Systems Journal 5, no. 2 (2020): 432–40. http://dx.doi.org/10.25046/aj050256.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Kakde, Mrs Kirti Pankaj, and Dr H. M. Padalikar. "Marathi Text Summarization using Extractive Technique." International Journal of Engineering and Advanced Technology 12, no. 5 (June 30, 2023): 99–105. http://dx.doi.org/10.35940/ijeat.e4200.0612523.

Full text

Abstract:

Multilingualism has played a key role in India, where people speak and understand more than one language. Marathi, as one of the official languages inMaharashtra state, is often used in sources such as newspapers or blogs. However, manually summarizing bulky Marathi paragraphs or texts for easy comprehension can be challenging. To address this, text summarization becomes essential to make large documents easily readable and understandable. This research article focuses on single document text summarization using the Natural Language Processing (NLP) approach, a subfield of Artificial Intelligence. Automatic text summarization is employed to extract relevant information in a concise manner. Information Extraction is particularly useful when summarizing documents consisting of multiple sentences into three or four sentences. While extensive research has been conducted on English Text Summarization, the field of Marathi document summarization remains largely unexplored. This research paper explores extractive text summarization techniques specifically for Marathi documents, utilizing the LexRank algorithm along with Genism, a graph-based technique, to generate informative summaries within word limit constraints. The experiment was conducted on the IndicNLP Marathi news article dataset, resulting in 78% precision, 72% recall, and 75% F-measure using the frequency-based method, and 78% precision, 78% recall, and 78% F-measure using the Lex Rank algorithm.

APA, Harvard, Vancouver, ISO, and other styles

12

Pise, N., and V. Gupta. "Rule based Stemmer for Marathi Language." International Journal of Computer Sciences and Engineering 6, no. 5 (May 31, 2018): 500–505. http://dx.doi.org/10.26438/ijcse/v6i5.500505.

Full text

APA, Harvard, Vancouver, ISO, and other styles

13

Wanjari, Nagmani, G. M. Dhopavkar, and Nutan B. Zungre. "Sentence Boundary Detection For Marathi Language." Procedia Computer Science 78 (2016): 550–55. http://dx.doi.org/10.1016/j.procs.2016.02.101.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Gaikwad, Ramnath Mahadeo, Rajashri Ganesh Kanke, and Manasi Ram Baheti. "Review on Sentiment Analysis of Marathi Language of Maharashtra." International Journal for Research in Applied Science and Engineering Technology 11, no. 8 (August 30, 2023): 345–49. http://dx.doi.org/10.22214/ijraset.2023.55149.

Full text

Abstract:

Abstract: Sentiment analysis on numerous Regional languages is performed, and classification algorithms based on Lexicon, Dictionary, and Machine Learning are employed. Because of the widespread usage of social media platforms, people are rapidly turning to the internet to find and discuss information, thoughts, opinions, feelings, perspectives, facts, and suggestions, resulting in a plethora of user-generated emotion enormous amounts of text data available for analysis. A large number of individuals in India express themselves in multiple languages, resulting in a massive amount of Natural Language Processing text data for (NLP) researchers. Sentiment Analysis (SA) of code-mixed text provides valuable information in politics, education, services marketing, business, health, sports, and other sectors. Work on Indian Language Sentiment Analysis Textual Data, particularly in Hindi, has gained steam in the previous decade in comparison to code-mixed Indian language text. However, due to a lack of language and vocabulary (linguistic and lexical) tools and annotated resources, the process of Sentiment Analysis of Regional Languages becomes very difficult. The goal of this research was to present a complete summary of the Sentiment Analysis of Regional languages, with a focus on code-mixed Regional languages.

APA, Harvard, Vancouver, ISO, and other styles

15

Rokade, Prajakta, Archana Kadam, Dipti Shinde, Shalini Yadav, and Neha Sali. "Indian Sign Language Recognition System in Marathi Language Text." International Journal of Computer Applications 182, no. 30 (December 17, 2018): 19–22. http://dx.doi.org/10.5120/ijca2018918202.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Rokade, Prajakta, Neha Sali, Dipti Shinde, and Shalini Yadav. "Indian Sign Language Recognition System in Marathi Language Text." International Journal of Computer Sciences and Engineering 7, no. 5 (May 31, 2019): 881–85. http://dx.doi.org/10.26438/ijcse/v7i5.881885.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Kulkarni-Joshi, Sonal. "Forty years of language contact and change in Kupwar: A critical assessment of the intertranslatability model." Journal of South Asian Languages and Linguistics 3, no. 2 (September 1, 2016): 147–74. http://dx.doi.org/10.1515/jsall-2016-0008.

Full text

Abstract:

AbstractThis paper revisits the language contact situation in the Indian border town-village of Kupwar originally reported by Gumperz and Wilson (1971. Convergence and creolization: A case from the Indo-Aryan/Dravidian border. In D. Hymes (ed.), Pidgnization and creolization of languages, 151–168. Cambridge: CUP). The study presents evidence for morpho-syntactic variation and complexification in the contact varieties of the local languages, Marathi and Kannada. Similar patterns of variation are adduced from contact varieties of Marathi and Kannada from historical data as well as present-day border villages which, like Kupwar, have been traditionally bilingual. The synchronic and historical data point out methodological and theoretical limitations of the original study. The variation and complexity observed in the Kupwar varieties allow for a reconsideration of the notion of intertranslatability or isomorphism in convergence areas. While suggesting a possible geographically defined micro-linguistic area at the Marathi-Kannada frontier, the paper indicates that the recent re-drawing of state boundaries along linguistic lines may have initiated divergence in this convergence area.

APA, Harvard, Vancouver, ISO, and other styles

18

Patil, Sandip S., R. P. Bhavsar, and B. V. Pawar. "ULMFiT Embedding(s) for Context and Extended Gloss Intersection for Marathi Word Sense Disambiguation." SAMRIDDHI : A Journal of Physical Sciences, Engineering and Technology 14, no. 04 (December 31, 2022): 126–32. http://dx.doi.org/10.18090/samriddhi.v14i04.20.

Full text

Abstract:

Ambiguities in the word meanings makes all the natural language processing (NLP) tasks very difficult, word sense disambiguation (WSD) is used to resolve these ambiguities. Now a day’s NLP-based human assistive systems are in demand, in which machines are expected to resolve word sense ambiguities. Today, due to the availability of machine readable dictionaries knowledge-based WSD approaches have become popular; it explores semantic relations between the contextual features and possible glosses of the given ambiguous word. Inductive transfer learning-based language models have great potential to represent the different semantic features of the word, which can be used in various NLP tasks. Universal language model fine-tuning for text classification (ULMFiT) is a popular transfer learning model used to embed various semantic features in digitally resource scare and morphologically rich language like marathi. In this reported work, the ambiguous words from the Marathi input sentence is extracted and have obtained its possible synset and glosses from IndoWordNet, these glosses are then extended using hypernym and hyponym relations. We have obtained the word embedding of marathi context and extended glosses using ULMFiT model. For the test run, we have crafted the test-bed of 6000 marathi sentences of 280 moderately ambiguous words harvested from marathi websites, which caters for 1200 senses. The winner sense is declared based on the maximum intersection score between the pair of context and gloss embedding. We have obtained the average accuracy up to 57.10% for our dataset.

APA, Harvard, Vancouver, ISO, and other styles

19

Shirsath, Nilesh, Aniruddha Velankar, Ranjeet Patil, and Shilpa Shinde. "Various Approaches of Machine Translation for Marathi to English Language." ITM Web of Conferences 40 (2021): 03026. http://dx.doi.org/10.1051/itmconf/20214003026.

Full text

Abstract:

Machine Translation (MT) is a generic term for computerised systems that generate translations from one natural language to another, with or without human intervention. Text may be used to examine knowledge, and turning that information into pictures helps people to communicate and acquire information.There seems to be a lot of work conducted on translating English to Hindi, Tamil, Bangla and other languages. The important parts of translation are to provide translated sentences with correct words and proper grammar. There has been a comprehensive review of 10 primary publications used in research. Two separate approaches are proposed, one uses rule based approach and other uses neural-machine translation approach to translate basic Marathi phrases to English. While designed primarily for Marathi-English language pairs, the design can be applied to other language pairs with a similar structure.

APA, Harvard, Vancouver, ISO, and other styles

20

Kamat, Rujvi, Manisha Ghate, Tamar H. Gollan, Rachel Meyer, Florin Vaida, Robert K. Heaton, Scott Letendre, et al. "Effects of Marathi-Hindi Bilingualism on Neuropsychological Performance." Journal of the International Neuropsychological Society 18, no. 2 (December 30, 2011): 305–13. http://dx.doi.org/10.1017/s1355617711001731.

Full text

Abstract:

AbstractThe present study aimed to examine if bilingualism affects executive functions and verbal fluency in Marathi and Hindi, two major languages in India, with a considerable cognate (e.g., activity is actividad in Spanish) overlap. A total of 174 native Marathi speakers from Pune, India, with varying levels of Hindi proficiency were administered tests of executive functioning and verbal performance in Marathi. A bilingualism index was generated using self-reported Hindi and Marathi proficiency. After controlling for demographic variables, the association between bilingualism and cognitive performance was examined. Degree of bilingualism predicted better performance on the switching (Color Trails-2) and inhibition (Stroop Color-Word) components of executive functioning; but not for the abstraction component (Halstead Category Test). In the verbal domain, bilingualism was more closely associated with noun generation (where the languages share many cognates) than verb generation (which are more disparate across these languages), as predicted. However, contrary to our hypothesis that the bilingualism “disadvantage” would be attenuated on noun generation, bilingualism was associated with an advantage on these measures. These findings suggest distinct patterns of bilingualism effects on cognition for this previously unexamined language pair, and that the rate of cognates may modulate the association between bilingualism and verbal performance on neuropsychological tests. (JINS, 2012, 18, 305–313)

APA, Harvard, Vancouver, ISO, and other styles

21

Kulkarni, Pallavi V., and Kalpana S. Thakre. "Developing sentiment lexicon for Marathi : A comprehensive survey and analysis." Journal of Information and Optimization Sciences 45, no. 4 (2024): 1141–52. http://dx.doi.org/10.47974/jios-1698.

Full text

Abstract:

Sentiment Analysis plays an important role in developing AI applications involving human language and sense. Language-specific Sentiment Lexicon is important to accelerate Sentiment Analysis. Marathi is a morphologically rich but low-resource Indic Language. The language has a very strong grammatical base showing high resemblance to the human body. The paper elaborates on issues like Lexicon basics, word embedding, and Neural Network Models in the process of Lexicon Construction. Existing databases that are useful as seed databases are enlisted. A detailed study of various methods of Lexicon Construction is done. The methods highlight that Sentiment Neural Embedding is required and contextual information plays a vital role in detecting the polarity of a single word or document. The hybrid approach which uses lexicon-based features for deep learning provides better understanding of sentiment analysis. A method is proposed for MSL construction and sentiment analysis of Marathi text. Natural Language Processing Research for Indic Language is its boom. For Marathi, the efforts are seen. Considering the depth and scope of this language, more resource creation is a must for its revolutionization.

APA, Harvard, Vancouver, ISO, and other styles

22

George, Annie Rachel, and Arnapurna Rath. "“Musk among Perfumes”." Church History and Religious Culture 96, no. 3 (2016): 304–24. http://dx.doi.org/10.1163/18712428-09603003.

Full text

Abstract:

The complexities of scriptural translation intensify in colonial, multilingual societies. In this study, we examine Thomas Stephens’s Kristapurana (1616) as a significant moment of cross-cultural encounters in the history of Bible translation in India. Stephens (1549–1619) was an English Jesuit, who worked in Goa, India. The Kristapurana is written in the Marathi language, in Roman script. Stephens’s Purana can be considered the first attempt to bring the biblical story into an Indian language, although in poetic form. This study aims to bring out the significance of this early Christian work in the Marathi language by analyzing Stephens’s translation of the biblical story into Marathi. The Kristapurana is studied as a site where Christianity and indigenous Hindu practices come together to form a “creative” expression of Christianity strongly reminiscent of the region that it was produced in.

APA, Harvard, Vancouver, ISO, and other styles

23

Jidge, Pooja, and Sharvari Govilkar. "Domain Specific Ontology Creation for Marathi Language." International Journal of Computer Applications 156, no. 13 (December 16, 2016): 6–9. http://dx.doi.org/10.5120/ijca2016912566.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

Govilkar, Sharvari, Bakal J. W, and Shubhangi Rathod. "Part of Speech Tagger for Marathi Language." International Journal of Computer Applications 119, no. 18 (June 18, 2015): 29–32. http://dx.doi.org/10.5120/21169-4245.

Full text

APA, Harvard, Vancouver, ISO, and other styles

25

Deodhar, Jayita K., Savita S. Goswami, and Lekhika N. Sonkusare. "Validation of the hospital anxiety depression scale - Marathi version in detecting anxiety and depression in cancer patients and caregivers." Indian Journal of Cancer 60, no. 3 (June 29, 2022): 345–52. http://dx.doi.org/10.4103/ijc.ijc_1321_20.

Full text

Abstract:

Abstract Background: The Hospital and Anxiety Depression Scale (HADS) is useful for screening depression and anxiety in cancer. It has not been validated in the Marathi language, which is the third most common language in India. We aimed to examine the reliability and validity of the Marathi-translated version of HADS in cancer patients and their caregivers. Methods: In a cross-sectional study design, we administered the Hospital and Anxiety Depression Scale-Marathi version (HADS-Marathi) to 100 participants (50 patients and 50 caregivers) after obtaining their informed consent. The team Psychiatrist, who was blind to the HADS-Marathi scores, interviewed all participants and identified the presence of anxiety and depressive disorders using the diagnostic criteria of the International Classification of Diseases – 10th edition. We measured internal consistency using Cronbach’s alpha, receiver operating characteristics, and factor structure. The study was registered with the Clinical Trials Registry-India (CTRI). Results: The internal consistency of HADS-Marathi was good with 0.815, 0.797, and 0.887 for anxiety and depression subscales and total scale, respectively. The area under curve figures were 0.836 (95% Confidence Interval [CI]: 0.756 - 0.915), 0.835 (95% [CI]: 0.749–0.921), and 0.879 (95% [CI] 0.806–0.951) for anxiety and depression subscales, and total scale, respectively. The best cutoffs identified were 8 (anxiety), 7 (depression), and 15 (total). The scale displayed a three-factor structure, with two depression subscale and one anxiety subscales items loading on to the third factor. Conclusion: We found that the HADS-Marathi version is a reliable and valid instrument for use in cancer patients. However, we found a three-factor structure, possibly reflecting a cross-cultural effect.

APA, Harvard, Vancouver, ISO, and other styles

26

Joshi, Reema, and Manisha Rathi. "Translation, cross-cultural adaptation, reliability, validation of King’s Health Questionnaire in the Marathi language." Indian Journal of Urology 40, no. 2 (April 2024): 96–100. http://dx.doi.org/10.4103/iju.iju_263_23.

Full text

Abstract:

ABSTRACT Introduction: Outcome measurement is a crucial component of contemporary professional practice. Many Indian rehabilitation facilities employ the King’s Health Questionnaire (KHQ), but there has never been an official Marathi translation with its reliability and validity. Materials and Methods: As per the recommendations for cross-cultural validation of an outcome assessment, KHQ was translated into the Marathi language at a tertiary hospital in Pune, India. A study was conducted to assess the dependability of 123 patients from tertiary hospitals in India. The reliability of the study was assessed by two competent physiotherapists. The interrater reliability of the KHQ total scores and each item was evaluated using Cronbach’s alpha coefficient. To compare the interrater dependability with the findings of other investigations, the intraclass correlation (ICC) coefficient was determined. Results: When evaluated by domain, the KHQ’s standardized Cronbach’s alpha ranged from 0.49–0.92. All domains had reliability that was rated as moderate to strong by ICC, and the severity rating scale varied from 0.53 to 0.81. The Pearson correlation coefficient between KHQ and short form-36 (SF-36) in the majority of related areas was found to be weak to moderate, with values ranging from −0.27 to −0.53. Conclusions: The Marathi version of the KHQ was translated and adapted for use in Marathi language-speaking Indian women with urinary incontinence complaints. It represents an important instrument for the evaluation of incontinent women in clinical research with good interrater reliability and validity with SF-36 quality-of-life measure.

APA, Harvard, Vancouver, ISO, and other styles

27

Patil, Ashwini, and Puneet Dwivedi. "Enhanced Recognition of Handwritten Marathi Compound Characters using CNN-SVM Hybrid Approach." Fusion: Practice and Applications 14, no. 2 (2024): 26–42. http://dx.doi.org/10.54216/fpa.140202.

Full text

Abstract:

This study presents a hybrid recognition system for multi-class compound Marathi characters, which addresses the problem of handwritten Marathi character recognition. The methodology efficiently bridges the gap between feature extraction and classification by integrating a Convolutional Neural Network (CNN) and Support Vector Machine (SVM). The first step is gathering and preprocessing a wide range of handwritten Marathi compound characters that are written in different styles. Using conventional supervised learning methods, the CNN is trained on this dataset, paying special attention to data augmentation and validation in order to reduce overfitting. High-level features taken from the final fully connected layer of the CNN are fed into an SVM classifier in the next step. By using these features in its training, the SVM improves prediction accuracy. For multi-class classification, the one-vs-all method is used. The hybrid CNN-SVM algorithm demonstrates its effectiveness in the crucial phases of feature extraction and classification by identifying handwritten compound Marathi characters with remarkable accuracy. Evaluation metrics, such as accuracy, precision, recall, F1-score, and confusion matrix analysis, are employed in the process of evaluating the effectiveness of the model. This assessment is carried out on a different testing dataset, offering a thorough examination of the model's functionality. The proposed algorithm demonstrates its superior performance and potential for improved character recognition by achieving training accuracy of 98.60% and validation accuracy of 97.69%. The development of handwriting recognition systems has benefited greatly from this research, especially when it comes to intricate scripts like Marathi. The suggested hybrid algorithm shows encouraging outcomes and has a great deal of potential for use in document processing, natural language comprehension, and character recognition in languages that use the Marathi script. Subsequent efforts will centre on refining the model and investigating ensemble methods to increase the robustness and accuracy of recognition.

APA, Harvard, Vancouver, ISO, and other styles

28

S. Govilkar, Sharvari, and Bakal J. W. "Question Answering System Using Ontology in Marathi Language." International Journal of Artificial Intelligence & Applications 8, no. 4 (July 30, 2017): 53–64. http://dx.doi.org/10.5121/ijaia.2017.8405.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Shinde, Amitkumar, and Ramesh Kagalkar. "Advanced Marathi Sign Language Recognition using Computer Vision." International Journal of Computer Applications 118, no. 13 (May 20, 2015): 1–7. http://dx.doi.org/10.5120/20802-3485.

Full text

APA, Harvard, Vancouver, ISO, and other styles

30

Chakraborty, Rahul, Nicole Morales, Kendell Fritsch, and Maria Diana Gonzales. "Second Language Proficiency and Maze: Marathi-English Bilinguals." Clinical Archives of Communication Disorders 2, no. 2 (August 31, 2017): 103–15. http://dx.doi.org/10.21849/cacd.2017.00101.

Full text

APA, Harvard, Vancouver, ISO, and other styles

31

Naik, Ramesh Ram, Maheshkumar B. Landge, and Namrata Mahender C. "Plagiarism Detection in Marathi Language Using Semantic Analysis." International Journal of Strategic Information Technology and Applications 8, no. 4 (October 2017): 30–39. http://dx.doi.org/10.4018/ijsita.2017100103.

Full text

Abstract:

In this article, the authors have proposed a method to detect plagiarism in the Marathi language by using semantic analysis. Nowadays, plagiarism is a challenging task in educational and research fields. Currently, there are some tools available to detect the plagiarism on the basis of similarity of words. But there is no tool available to detect the plagiarism semantically. In this article, the authors have applied preprocessing to a database i.e. tokenization, removed stop words and punctuations, for the goal of calculating the frequency of words. Then searching the same word or synonyms of words in wordnet to detect the semantic plagiarism. It is useful for many researchers who are working in this domain.

APA, Harvard, Vancouver, ISO, and other styles

32

Musale, Sandeep, Kalyani Gargate, Vaishnavi Gulavani, Samruddhi Kadam, and Shweta Kothawade. "Indian sign language recognition and search results." Journal of Autonomous Intelligence 6, no. 3 (August 22, 2023): 1000. http://dx.doi.org/10.32629/jai.v6i3.1000.

Full text

Abstract:

<p>Sign language is a medium of communication for people with hearing and speaking impairment. It uses gestures to convey messages. The proposed system focuses on using sign language in search engines and helping specially-abled people get the information they are looking for. Here, we are using Marathi sign language. Translation systems for Indian sign languages are not much simple and popular as American sign language. Marathi language consists of words with individual letters formed of two letter = Swara + Vyanjan (Mulakshar). Every Vyanjan or Swara individually has a unique sign which can be represented as image or video with still frames. Any letter formed of both Swara and Vyanjan is represented with hand gesture signing the Vyanjan as above and with movement of signed gesture in shape of Swara in Devnagari script. Such letters are represented with videos containing motion and frames in particular sequence. Further the predicted term can be searched on google using the sign search. The proposed system includes three important steps: 1) hand detection; 2) sign recognition using neural networks; 3) fetching search results. Overall, the system has great potential to help individuals with hearing and speaking impairment to access information on the internet through the use of sign language. It is a promising application of machine learning and deep learning techniques.</p>

APA, Harvard, Vancouver, ISO, and other styles

33

Nemade, Vedant. "Exploring Sentiment Analysis in Indian Regional Languages: Methods, Challenges, and Future Directions." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 04 (April 2, 2024): 1–5. http://dx.doi.org/10.55041/ijsrem29963.

Full text

Abstract:

Sentiment Analysis, pivotal in natural language processing, extends its reach beyond English to Indian regional languages like Hindi, Marathi, Kannada, Konkani, Bengali, Khandeshi, and Urdu. This paper presents a comprehensive survey of 32 research papers in this domain, examining methodologies, datasets, and techniques while emphasizing the significance of sentiment analysis in diverse linguistic contexts for enhancing customer relationship management functionalities. It underscores the necessity for future research and highlights the efficacy of machine learning techniques. By elucidating on computational challenges and outlining various sentiment analysis methods, this paper serves as a critical resource for researchers and practitioners, fostering advancements in sentiment analysis tailored to regional linguistic nuances. KEYWORDS Bag Of Words, Hindi, Kannada, RNN, Konkani, Malayalam, Marathi, Maximum Entropy, Naive Bayes, Sentiment Analysis, SVM, TF-IDF, Urdu.

APA, Harvard, Vancouver, ISO, and other styles

34

Shah, Sonali Rajesh, Abhishek Kaushik, Shubham Sharma, and Janice Shah. "Opinion-Mining on Marglish and Devanagari Comments of YouTube Cookery Channels Using Parametric and Non-Parametric Learning Models." Big Data and Cognitive Computing 4, no. 1 (March 17, 2020): 3. http://dx.doi.org/10.3390/bdcc4010003.

Full text

Abstract:

YouTube is a boon, and through it people can educate, entertain, and express themselves about various topics. YouTube India currently has millions of active users. As there are millions of active users it can be understood that the data present on the YouTube will be large. With India being a very diverse country, many people are multilingual. People express their opinions in a code-mix form. Code-mix form is the mixing of two or more languages. It has become a necessity to perform Sentiment Analysis on the code-mix languages as there is not much research on Indian code-mix language data. In this paper, Sentiment Analysis (SA) is carried out on the Marglish (Marathi + English) as well as Devanagari Marathi comments which are extracted from the YouTube API from top Marathi channels. Several machine-learning models are applied on the dataset along with 3 different vectorizing techniques. Multilayer Perceptron (MLP) with Count vectorizer provides the best accuracy of 62.68% on the Marglish dataset and Bernoulli Naïve Bayes along with the Count vectorizer, which gives accuracy of 60.60% on the Devanagari dataset. Multilayer Perceptron and Bernoulli Naïve Bayes are considered to be the best performing algorithms. 10-fold cross-validation and statistical testing was also carried out on the dataset to confirm the results.

APA, Harvard, Vancouver, ISO, and other styles

35

Kharate, Namrata G., and Varsha H. Patil. "Inflection rules for Marathi to English in rule based machine translation." IAES International Journal of Artificial Intelligence (IJ-AI) 10, no. 3 (September 1, 2021): 780. http://dx.doi.org/10.11591/ijai.v10.i3.pp780-788.

Full text

Abstract:

Machine translation is important application in natural language processing. Machine translation means translation from source language to target language to save the meaning of the sentence. A large amount of research is going on in the area of machine translation. However, research with machine translation remains highly localized to the particular source and target languages as they differ syntactically and morphologically. Appropriate inflections result correct translation. This paper elaborates the rules for inflecting the parts-of-speech and implements the inflection for Marathi to English translation. The inflection of nouns, pronouns, verbs, adjectives are carried out on the basis of semantics of the sentence. The results are discussed with examples.

APA, Harvard, Vancouver, ISO, and other styles

36

TARE, MEDHA, and SUSAN A. GELMAN. "Bilingual parents' modeling of pragmatic language use in multiparty interactions." Applied Psycholinguistics 32, no. 4 (April 7, 2011): 761–80. http://dx.doi.org/10.1017/s0142716411000051.

Full text

Abstract:

ABSTRACTParental input represents an important source of language socialization. Particularly in bilingual contexts, parents may model pragmatic language use and metalinguistic strategies to highlight language differences. The present study examines multiparty interactions involving 28 bilingual English- and Marathi-speaking parent–child pairs in the presence of monolingual bystanders (children's mean ages = 3 years, 2 months and 4 years, 6 months). Their language use was analyzed during three sessions: parent and child alone, parent and child with the English speaker, and parent and child with the Marathi speaker. Parents demonstrated pragmatic differentiation by using relatively more of the bystander's language; however, children did not show this sensitivity. Further, parents used a variety of strategies to discuss language differences, such as providing and requesting translations; children translated most often in response to explicit requests. The results indicate that parents model pragmatic language differentiation as well as metalinguistic talk that may contribute to children's metalinguistic awareness.

APA, Harvard, Vancouver, ISO, and other styles

37

Tahakik, Sanskruti, and Doss Prakash. "Validity and Reliability of Marathi Translated Modified Polycystic Ovary Syndrome Questionnaire (MARmPCOSQ)." International Journal of Health Sciences and Research 12, no. 4 (April 19, 2022): 231–35. http://dx.doi.org/10.52403/ijhsr.20220426.

Full text

Abstract:

PCOS is Considered composite disease with wide range of manifestations which affect Quality of life of females, there are various questionnaires to Assess quality of life but mPCOSQ is more valid and reliable tool, but some females in our region don’t understand English language for assessment of their quality of life there was need of translation and validation of mPCOSQ in Marathi. A Cross sectional study conducted on 78 women speaking Marathi language. Participants included in study with mean Age 22.9±4.6 and BMI 24.7 ± 2.7 respectively most of them diagnosed with PCOS for ≥ 1 year. All experts rated translated items of the mPCOSQ as clinically relevant with comments on few items that were modified the Content validity index (CVI) for MARmPCOSQ was 0.9. The internal consistency for reliability, the alpha coefficient was 0.92 indicating good reliability. The interclass co-relation Coefficient for each item were also acceptable, ranging from 0.921 to 0.978 with p value < 0.001. which shows that the scale has good Reliability. Key words: PCOS, Marathi Translated PCOS, PCOSQ, Polycystic ovary syndrome Questionnaire.

APA, Harvard, Vancouver, ISO, and other styles

38

Ravishankar, Vinit. "Finite-State Back-Transliteration for Marathi." Prague Bulletin of Mathematical Linguistics 108, no. 1 (June 1, 2017): 319–29. http://dx.doi.org/10.1515/pralin-2017-0030.

Full text

Abstract:

AbstractIn this paper, we describe the creation of an open-source, finite-state based system for back-transliteration of Latin text in the Indian language Marathi. We outline the advantages of our system and compare it to other existing systems, evaluate its recall, and evaluate the coverage of an open-source morphological analyser on our back-transliterated corpus.

APA, Harvard, Vancouver, ISO, and other styles

39

Walunj, Parmesh, Krupa Shah, Rishi Tank, Atharva Mathure, Ritesh Shekhar, and Ms Deepali Kadam. "Tag Recommendation System for Marathi News Articles by using Multi-label Classification." International Journal for Research in Applied Science and Engineering Technology 11, no. 4 (April 30, 2023): 2305–11. http://dx.doi.org/10.22214/ijraset.2023.50626.

Full text

Abstract:

Abstract: Multi-label classification is the variant of a classification problem where multiple labels are assigned to each instance. In multi-label classification, the training set is composed of instances each associated with a set of labels, and the task is to predict the label sets of unseen instances through analyzing training instances with known label sets. This paper demonstrates the use of multi-label classification to determine tags for news articles written in the Marathi Language of India. The proposed study uses Binary Relevance (One vs Rest) technique of multi-label classification to establish the tags for the given input of a Marathi news article. Tag recommendation systems for Marathi news articles can greatly enhance the user experience for readers and help them find the articles that are most relevant to their interests.

APA, Harvard, Vancouver, ISO, and other styles

40

Patil, Nita V. "POS Tagging for Marathi Language using Hidden Markov Model." International Journal of Computer Sciences and Engineering 6, no. 1 (January 31, 2018): 409–12. http://dx.doi.org/10.26438/ijcse/v6i1.409412.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

GAIKWAD, SANTOSH, BHARTI GAWALI, and MEHROTRA SC. "POLLY CLINIC INQUIRY SYSTEM USING IVR IN MARATHI LANGUAGE." International Journal of Machine Intelligence 3, no. 3 (November 30, 2011): 142–45. http://dx.doi.org/10.9735/0975-2927.3.3.142-145.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Patil, Amit, Chhaya Patli, Rakesh Ramteke, Bhavsar R. P., and Hemant Darbari. "Exploring Resources in Word Sense Disambiguation for Marathi Language." International Research Journal on Advanced Science Hub 2, Special Issue ICAMET 10S (December 2, 2020): 108–11. http://dx.doi.org/10.47392/irjash.2020.207.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Kayte, Sangramsing, Monica Mundada, and Charansing Kayte. "Performance Evaluation of Speech Synthesis Techniques for Marathi Language." International Journal of Computer Applications 130, no. 3 (November 17, 2015): 45–50. http://dx.doi.org/10.5120/ijca2015907023.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Nathusing, Sangramsing. "Text To Speech for Marathi Language using Transcriptions Theory." International Journal of Computer Applications 131, no. 6 (December 17, 2015): 39–41. http://dx.doi.org/10.5120/ijca2015907492.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

., Gauri Dhopavkar. "EXPLOITING RULES FOR RESOLVING AMBIGUITY IN MARATHI LANGUAGE TEXT." International Journal of Research in Engineering and Technology 04, no. 12 (December 25, 2015): 268–73. http://dx.doi.org/10.15623/ijret.2015.0412053.

Full text

APA, Harvard, Vancouver, ISO, and other styles

46

Prabha, Chandra, and Ramesh Vaman Dhongde. "Tense, Aspect, Mood in English and Marathi." Language 64, no. 4 (December 1988): 836. http://dx.doi.org/10.2307/414604.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

Rosen, Carol, and Kashi Wali. "Twin Passives, inversion and multistratalism in Marathi." Natural Language and Linguistic Theory 7, no. 1 (February 1989): 1–50. http://dx.doi.org/10.1007/bf00141346.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Waghmare, Chaitali M., Hemant J. Pawar, Vandana S. Jain, Arya Bhanu, Pradeep K. Thakur, and Padmini H. Nirmal. "Marathi Translation and Linguistic Validation of an Updated European Organization for Research and Treatment of Cancer Quality of Life Module for Head and Neck." South Asian Journal of Cancer 09, no. 04 (October 2020): 199–203. http://dx.doi.org/10.1055/s-0041-1729444.

Full text

Abstract:

Abstract Aim This study was aimed to translate an updated European Organization for Research and Treatment of Cancer (EORTC) quality of life module for head and neck (EORTC QLQ-H&N43) in grammatically and conceptually acceptable Marathi language and its linguistic validation. Materials and Methods Approval was obtained from the Institutional Ethics Committee. The permission for translation was obtained from the EORTC translation unit (TU). The EORTC guidelines for the translation were followed to form a translation for pilot testing which was administered to 10 Marathi speaking head and neck squamous cell cancer (HNSCC) patients who gave informed written consent for the participation in the study. Patients were interviewed personally. The final Marathi translation was prepared and sent to EORTC TU for approval. Statistical analysis was performed using SYSTAT version 12 by Cranes software, Bengaluru, Karnataka, India. Results After getting permission, the translation files were received from EORTC TU, including Marathi EORTC QLQ-H&N35 for reference. Two forward translations, reconciled translation, back translations, first interim translation, translation for proof editing, and second interim translation (SIT) were prepared. This SIT was pilot tested in 10 Marathi-speaking HNSCC patients. Each patient was interviewed regarding difficulty in answering, confusing or offensive word, and reframing sentence. The questionnaire was well understood by patients reflecting its linguistic validity. After incorporating the changes as per the patient’s interview, updated translation was prepared and sent to EORTC TU which was accepted and approved by EORTC. The psychometric analysis of pilot testing showed that the questionnaire is acceptable. Conclusion Marathi translation of EORTC QLQ-H&N43 is well accepted and understandable. It can be used for future studies.

APA, Harvard, Vancouver, ISO, and other styles

49

Yeolekar, Aditya M., Vidya Rokade, Kiran Shinde, Netra Pathak, Haris Qadri, and Kaustubh Kahane. "Sino-Nasal Outcome Test-22: Translation, Cross-cultural Adaptation, and Validation in Local Language." Bengal Journal of Otolaryngology and Head Neck Surgery 26, no. 1 (April 28, 2018): 10–15. http://dx.doi.org/10.47210/bjohns.2018.v26i1.150.

Full text

Abstract:

Introduction Quality of life questionnaires have been increasingly used in clinical studies to help estimate the magnitude of problem. Sino-Nasal Outcome Test -22 (SNOT-22) is considered to be a good tool to measure the severity of Sino-Nasal Diseases. As this test is in English, it may be difficult for the local population to express their symptoms correctly. Therefore we have translated and validated the SNOT- 22 test in local Indian language, Marathi. Materials and Methods An early Indian ( Marathi ) version of the SNOT 22 questionnaire was prepared. This was a prospective study,where forty patients with Sino-nasal Diseases confirmed on DNE & CT(PNS) filled the questionnaire. This was repeated after a period of 14 days to retest. For validation the questionnaire was also filled by healthy individuals. Results The mean SNOT-22 score ± SD was 50.17 ± 18.65 (range 10–93) in the initial test, and 49.61 ± 18.40 (range 21–91) in retest in the study group. Cronbach’s alpha was 0.835 and 0.837 at the initial and retest examination respectively, both values were suggesting a good internal consistency. The mean SNOT-22 score ± SD was 13 ± 11.68 in the control group and 49.61 ± 18.40 (range 21–91) in the sino-nasal disease group and proved by Mann- Whitney U test. Conclusion The Marathi SNOT-22 is a valid instrument to assess the symptomatology of patients of Sino-nasal Diseases in Maharashtra.

APA, Harvard, Vancouver, ISO, and other styles

50

Tangsali, Rahul, Swapnil Chhatre, Soham Naik, Pranav Bhagwat, and Geetanjali Kale. "Evaluating Performances of Attention-Based Merge Architecture Models for Image Captioning in Indian Languages." Journal of Image and Graphics 11, no. 3 (September 2023): 294–301. http://dx.doi.org/10.18178/joig.11.3.294-301.

Full text

Abstract:

Image captioning is a growing topic of research in which numerous advancements have been made in the past few years. Deep learning methods have been used extensively for generating textual descriptions of image data. In addition, attention-based image captioning mechanisms have also been proposed, which give state-ofthe- art results in image captioning. However, many applications and analyses of these methodologies have not been made in the case of languages from the Indian subcontinent. This paper presents attention-based merge architecture models to achieve accurate captions of images in four Indian languages- Marathi, Kannada, Malayalam, and Tamil. The widely known Flickr8K dataset was used for this project. Pre-trained Convolutional Neural Network (CNN) models and language decoder attention models were implemented, which serve as the components of the mergearchitecture proposed here. Finally, the accuracy of the generated captions was compared against the gold captions using Bilingual Evaluation Understudy (BLEU) as an evaluation metric. It was observed that the merge architectures consisting of InceptionV3 give the best results for the languages we test on, the scores discussed in the paper. Highest BLEU-1 scores obtained for each language were: 0.4939 for Marathi, 0.4557 for Kannada, 0.5082 for Malayalam, and 0.5201 for Tamil. Our proposed architectures gave much higher scores than other architectures implemented for these languages.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Marathi language'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles