Journal articles: 'Post-editing'

1

Han, Hyun Hee. "Pre-editing and post-editing guidelines for Russian to Korean machine translation." Korean Journal of Russian Language and Literature 31, no. 4 (December 31, 2019): 65–96. http://dx.doi.org/10.38077/kjrll.2019.12.31.4.65.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Barade, Vikram. "The Role of Video Editing in Post Production." International Journal of Science and Research (IJSR) 12, no. 8 (August 5, 2023): 1152–53. http://dx.doi.org/10.21275/sr23812195230.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Stasimioti, Maria, Vilelmini Sosoni, and Konstantinos Chatzitheodorou. "Investigating post-editing effort." Developments in Cognitive Translation and Interpreting Studies 8, no. 2 (November 22, 2021): 378–403. http://dx.doi.org/10.1075/cogls.00083.sta.

Full text

Abstract:

Abstract The working environment of translators has changed significantly in recent decades, with post-editing (PE) emerging as a new trend in the human translation workflow, particularly following the advent of neural machine translation (NMT) and the improvement of the quality of the machine translation (MT) raw output especially at the level of fluency. In addition, the directionality axiom is increasingly being questioned with translators working from and into their first language both in the context of translation (Buchweitz and Alves 2006; Pavlović and Jensen 2009; Fonseca and Barbosa 2015; Hunziker Heeb 2015; Ferreira 2013, 2014; Ferreira et al. 2016; Feng 2017) and in the context of PE (Garcia 2011; Sánchez-Gijón and Torres-Hostench 2014; da Silva et al. 2017; Toledo Báez 2018). In this study we employ product- and process-oriented approaches to investigate directionality in PE in the English-Greek language pair. In particular, we compare the cognitive, temporal, and technical effort expended by translators for the full PE of NMT output in L1 (Greek) with the effort required for the full PE of NMT output in L2 (English), while we also analyze the quality of the final translation product. Our findings reveal that PE in L2, i.e., inverse PE, is less demanding than PE in L1, i.e., direct PE, in terms of the time and keystrokes required, and the cognitive load exerted on translators. Finally, our research shows that directionality does not imply differences in quality.

APA, Harvard, Vancouver, ISO, and other styles

4

Candel-Mora, Miguel Angel, and Carla Borja-Tormo. "Development of the app Post-editing Calculeffort to calculate post-editing effort." Tradumàtica: tecnologies de la traducció, no. 15 (December 29, 2017): 1. http://dx.doi.org/10.5565/rev/tradumatica.190.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Lee, Junho. "A study for post-editing education : Difference between post-editing and human translation." Interpretation and Translation 20, no. 1 (April 10, 2018): 73–96. http://dx.doi.org/10.20305/it201801073096.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Flórez Giraldo, Silvia. "Catalogue of post-editing tools." Tradumàtica: tecnologies de la traducció, no. 10 (February 5, 2013): 219. http://dx.doi.org/10.5565/rev/tradumatica.26.

Full text

APA, Harvard, Vancouver, ISO, and other styles

7

Lapinskaitė, Dalia, and Dalia Mankauskienė. "MOOC Coursera Content Post-editing." Vertimo studijos 15 (December 30, 2022): 6–29. http://dx.doi.org/10.15388/vertstud.2022.1.

Full text

Abstract:

This paper presents the post-editing features of the machine translation (MT) system Smartling used to translate the learning content of MOOC (Massive Open Online Course) Coursera. Most of the Coursera content is delivered in English, which is one of the reasons for the low uptake of these courses in Lithuania. With the growing demand for online resources, the need to translate courses into Lithuanian has become evident and MT systems are increasingly used for that purpose. This paper describes the results of an experiment carried out with the Smartling MT system. The experiment involved 10 participants, 6 professional and 4 non-professional translators, who post-edited a passage from the Coursera course The Science of Wellbeing. The post-editing process was monitored using the Translog-II tool, which captures the participants‘ keystrokes. The paper presents the classification and frequency of MT errors. One of the most important post-editing features of the Smartling MT system is the splitting of the text into subtitle lines, which is the cause of most grammatical errors. Among the errors not attributable to this text division are those caused by the polysemy of the words, literal translation and the use of pronouns. After the post-editing task, participants filled in a short questionnaire about the functionality of the Smartling system. 7 out of 10 participants rated the performance of this system as satisfactory. The results of the study showed that Smartling is not sufficiently tailored to the Lithuanian language, and that translators have to use a lot of cognitive effort in post-editing.

APA, Harvard, Vancouver, ISO, and other styles

8

O’Brien, Sharon. "Towards predicting post-editing productivity." Machine Translation 25, no. 3 (September 2011): 197–215. http://dx.doi.org/10.1007/s10590-011-9096-7.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Jia, Yanfang, and Binghan Zheng. "The interaction effect between source text complexity and machine translation quality on the task difficulty of NMT post-editing from English to Chinese: A multi-method study." Across Languages and Cultures 23, no. 1 (May 9, 2022): 36–55. http://dx.doi.org/10.1556/084.2022.00120.

Full text

Abstract:

Abstract This study explores the interaction effect between source text (ST) complexity and machine translation (MT) quality on the task difficulty of neural machine translation (NMT) post-editing from English to Chinese. When investigating human effort exerted in post-editing, existing studies have seldom taken both ST complexity and MT quality levels into account, and have mainly focused on MT systems used before the emergence of NMT. Drawing on process and product data of post-editing from 60 trainee translators, this study adopted a multi-method approach to measure post-editing task difficulty, including eye-tracking, keystroke logging, quality evaluation, subjective rating, and retrospective written protocols. The results show that: 1) ST complexity and MT quality present a significant interaction effect on task difficulty of NMT post-editing; 2) ST complexity level has a positive impact on post-editing low-quality NMT (i.e., post-editing task becomes less difficult when ST complexity decreases); while for post-editing high-quality NMT, it has a positive impact only on the subjective ratings received from participants; and 3) NMT quality has a negative impact on its post-editing task difficulty (i.e., the post-editing task becomes less difficult when MT quality goes higher), and this impact becomes stronger when ST complexity increases. This paper concludes that both ST complexity and MT quality should be considered when testing post-editing difficulty, designing tasks for post-editor training, and setting fair post-editing pricing schemes.

APA, Harvard, Vancouver, ISO, and other styles

10

Ali Alshehri, Bodour, and Noha Abdullah Alowedi. "Saudi Translation Agencies and Translation Centers: A Study of Post-Editing Practices." World Journal of English Language 13, no. 3 (February 24, 2023): 118. http://dx.doi.org/10.5430/wjel.v13n3p118.

Full text

Abstract:

This qualitative research aims to investigate and analyze the practice of post-editing activity in Saudi translation agencies and translation centers. The study’s focus is on the importance of post-editing Machine Translation (MT) output as an approach to upgrade the quality of MT results to enhance the accuracy of translations. The study data were collected through an electronic survey (questionnaire) comprising short questions about post-editing practice and guidelines in addition to their knowledge about post-editing certification programs. The participants in this study were 18 professional translators working in certified translation agencies and translation centers across different universities between Jeddah, Dammam, and Riyadh cities. The results of the study showed that the participants post-edited the MT outputs in their tasks and recognized the importance of being aware of post-editing standards and guidelines. Further, the findings demonstrated that the majority of the participants used machine translation tools. Finally, they were positively disposed about post-editing certification programs to take employment as post-editors. Based on the results of this study, it is recommended to analyze the state of post-editing in Saudi Arabia on a larger sample to investigate the attitudes of Saudi translation students towards practicing post-editing of MT outputs, and analyzing the activity of post-editing MT in specialized texts by Saudi professional translators.

APA, Harvard, Vancouver, ISO, and other styles

11

Werstine, Paul. "Post-Theory Problems in Shakespeare Editing." Yearbook of English Studies 29 (1999): 103. http://dx.doi.org/10.2307/3508937.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Navarro, Ignasi. "Content post-editing in daily publications." Tradumàtica: tecnologies de la traducció, no. 10 (February 5, 2013): 185. http://dx.doi.org/10.5565/rev/tradumatica.20.

Full text

APA, Harvard, Vancouver, ISO, and other styles

13

Mitchell, Linda, Sharon O’Brien, and Johann Roturier. "Quality evaluation in community post-editing." Machine Translation 28, no. 3-4 (November 21, 2014): 237–62. http://dx.doi.org/10.1007/s10590-014-9160-1.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Blagodarna, Olena. "Insights into post-editors’ profiles and post-editing practices." Tradumàtica: tecnologies de la traducció, no. 16 (December 3, 2018): 35. http://dx.doi.org/10.5565/rev/tradumatica.198.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Escartín, Carla Parra, Hanna Béchara, and Constantin Orăsan. "Questing for Quality Estimation A User Study." Prague Bulletin of Mathematical Linguistics 108, no. 1 (June 1, 2017): 343–54. http://dx.doi.org/10.1515/pralin-2017-0032.

Full text

Abstract:

AbstractPost-Editing of Machine Translation (MT) has become a reality in professional translation workflows. In order to optimize the management of projects that use post-editing and avoid underpayments and mistrust from professional translators, effective tools to assess the quality of Machine Translation (MT) systems need to be put in place. One field of study that could address this problem is Machine Translation Quality Estimation (MTQE), which aims to determine the quality of MT without an existing reference. Accurate and reliable MTQE can help project managers and translators alike, as it would allow estimating more precisely the cost of post-editing projects in terms of time and adequate fares by discarding those segments that are not worth post-editing (PE) and have to be translated from scratch.In this paper, we report on the results of an impact study which engages professional translators in PE tasks using MTQE. We measured translators’ productivity in different scenarios: translating from scratch, post-editing without using MTQE, and post-editing using MTQE. Our results show that QE information, when accurate, improves post-editing efficiency.

APA, Harvard, Vancouver, ISO, and other styles

16

Chen, Xu, and Yousun Shin. "Comparative Analysis of Post-editing Techniques for Chinese-to-English Translation Tasks: A Quasi-Experimental Study." British and American Language and Literature Association of Korea 149 (June 30, 2023): 147–71. http://dx.doi.org/10.21297/ballak.2023.149.147.

Full text

Abstract:

This study aimed to examine the differences in translation time and quality between human translation (HT), machine translation post-editing (MTPE), and ChatGPT post-editing (ChatGPT PE). A quasi-experimental design was employed, involving 30 junior participants majoring in English from a Chinese university. A translation task consisting of 532 words from Chinese to English was assigned to the three groups and the translation speed and quality were assessed using the Multidimensional Quality Metrics (MQM) and Dynamic Quality Framework (DQF). The results demonstrated that the post-editing technique could produce translation quality comparable to human translation while achieving faster translation speed. It was observed that ChatGPT PE outputs exhibited the highest number of terminology errors but had the fewest accuracy errors, while mean differences in two of accuracy dimensions were observed among the three groups. The utilization of post-editing in language teaching would allow for the integration of machine translation strengths and human expertise, resulting in high-quality translations on par with human translations. To optimize post-editing outcomes, it is crucial to develop and teach error-detection techniques and avoid excessive reliance on AI technology.

APA, Harvard, Vancouver, ISO, and other styles

17

Isosävi, Johanna, and Leena Salmi. "Kääntäjäopiskelijoiden käsityksiä jälkieditoinnista." Mikael: Kääntämisen ja tulkkauksen tutkimuksen aikakauslehti 10 (April 1, 2017): 121–35. http://dx.doi.org/10.61200/mikael.129425.

Full text

Abstract:

This paper presents a study on translator student’s perceptions on post-editing. Students from two different Master’s level courses were asked to post-edit machine translated texts and reflect on the differences between light and full post-editing, on the differences between translating and post-editing, on the role of error analysis and the use of the instructions given, as well as consider their own aptitudes in post-editor. The results show that their attitudes were mainly positive, but they felt that the task was challenging: leaving grammatical errors and “raw translations” in the text were considered difficult. The majority of students also thought that making a full post-editing was easier than making a light post-editing. This was also reflected in their productions, as many students returned a light edit that corresponded to a full one.

APA, Harvard, Vancouver, ISO, and other styles

18

DEDE, Volkan, and Elena ANTONOVA-ÜNLÜ. "Does a Formal Post-editing Training Affect the Performance of Novice Post-editors? An Experimental Study." Cankaya University Journal of Humanities and Social Sciences 16, no. 2 (December 6, 2022): 131–48. http://dx.doi.org/10.47777/cankujhss.1106326.

Full text

Abstract:

Machine translation systems led to the creation of a new role for translators: the post-editor. With the birth of neural machine translation systems, the demand for post-editing has been increasing in the recent years, and it has now become a common service given by language service providers and professional translators. Such a change in the landscape of the translation industry might evolve the translation training programs worldwide. It is still heavily discussed whether post-editing and translation skills overlap, and post-editing courses are now included into the curriculum by several translation departments. We set out to investigate whether post-editing training influences the performance of student post-editors in order to explore the necessary background and skills in post-editing tasks. We measured productivity parameters and quality of the final outputs produced by two groups of participants, one of which was previously trained on post-editing. Our results show that, the experimental and control groups did not differ significantly from each other in terms of productivity. There was also little to no difference when we evaluated the post-edited outputs produced by both groups against a reference text using automatic machine translation evaluation metrics. However, we detected a statistical significance between the groups when we analyzed the number of errors in the final output. The post-editors in the experimental group were more aware of the typical errors of machine translation engines.

APA, Harvard, Vancouver, ISO, and other styles

19

Surya Kukuh, Muhammad, Paundra Haikal, and Ananda Gusmadana. "Manajemen Post Production Editing pada Film Malam." Jurnal Audiens 4, no. 2 (May 31, 2023): 341–50. http://dx.doi.org/10.18196/jas.v4i2.50.

Full text

Abstract:

Mengenai Manajemen Post Production Editing yang digunakan pada film Malam, Proses editing yang dimaksud adalah bagaimana crew post productionmengolah audio visual dari film tersebut kemudian disatukan menjadi film yang memiliki sense of belong kepada audiens. Post production atau pasca produksi merupakan bagian terakhir dari proses pembuatan film yaitu penyuntingan dengan memadukan hasil rekaman menjadi cerita yang utuh. Penelitian ini termasuk dalam penelitian deskriptif kualitatif karena berdasarkan rumusan masalah yang telah dijelaskan, penelitian ini bertujuan untuk menguji Manajemen PostProduction Pada Film Malam. Editing merupakan salah satu bagian penting dalam produksi film karena melalui proses ini, kita dapat menentukan keberhasilan atau kegagalan sebuah film. Pemilihan editor yang tepat sangatlah penting untuk kesuksesan sebuah film. Tahapan editing dalam film sendiri tentu memiliki struktur yang berbeda-beda dalam tahapan post produksi. Pada film Malam, tahapan post produksi yaitu tahapan editing sistem kerja yang digunakan melibatkan dua orang, yaitu seorang Digital Imaging Technician (DIT) dan editor. Walaupun dalam proses syuting film terdapat perbedaan struktur khususnya dalam postproduksi, pemilihan kru post produksi film Malam dirasa sudah sangat ideal. Namun tak bisa dipungkiri setiap kru atau tim yang dibentuk pasti memiliki kendala masing-masing.

APA, Harvard, Vancouver, ISO, and other styles

20

de Faria Pires, Loïc. "Master’s students’ post-editing perception and strategies." FORUM / Revue internationale d’interprétation et de traduction / International Journal of Interpretation and Translation 18, no. 1 (June 16, 2020): 26–44. http://dx.doi.org/10.1075/forum.19014.pir.

Full text

Abstract:

Abstract The present article aims at presenting the results of an exploratory post-editing process study carried out in a Belgian university, the University of Mons. For this experiment, 64 final-year translation students with no post-editing experience post-edited from English into French parts of five different institutional texts from the Directorate-General for Translation (DGT) of the European Commission. They were additionally asked to fill in a prospective questionnaire and a retrospective one, related to their post-editing perception and strategies. Four students took part in the experiment on a separate computer equipped with an eye-tracking device, so that eye-tracking data could be collected and compared with these students’ questionnaires. We found that results related to eye-tracking data correlate well with previous research, and that students’ perceptions of post-editing depend on each university’s particular context.

APA, Harvard, Vancouver, ISO, and other styles

21

Fernández Torné, Anna, and Anna Matamala. "Human evaluation of three machine translation systems: from quality to attitudes by professional translators." Vigo International Journal of Applied Linguistics, no. 18 (January 18, 2021): 123–48. http://dx.doi.org/10.35869/vial.v0i18.3366.

Full text

Abstract:

This article aims to compare three machine translation systems with a focus on human evaluation. The systems under analysis are a domain-adapted statistical machine translation system, a domain-adapted neural machine translation system and a generic machine translation system. The comparison is carried out on translation from Spanish into German with industrial documentation of machine tool components and processes. The focus is on the human evaluation of the machine translation output, specifically on: fluency, adequacy and ranking at the segment level; fluency, adequacy, need for post-editing, ease of post-editing, and mental effort required in post-editing at the document level; productivity (post-editing speed and post-editing effort) and attitudes. Emphasis is placed on human factors in the evaluation process.

APA, Harvard, Vancouver, ISO, and other styles

22

Gusieva, Olena. "Automated translation and its “Post-machine” editing." Vìsnik Marìupolʹsʹkogo deržavnogo unìversitetu. Serìâ: Fìlologìâ 15, no. 26-27 (2022): 261–67. http://dx.doi.org/10.34079/2226-3055-2022-15-26-27-261-267.

Full text

Abstract:

The article examines the peculiarities of text editing, in cases the translation is performed by using one of the automated translation systems. The relevance of the study is justified by the widespread use of automated translation programs, on the one hand, and the insufficient quality of machine translations, on the other. The introduction of automated systems into the practice of translation allows the analysis of machine translation texts to be included in the range of research tasks. In the applied aspect, there is a need to develop training courses that highlight the issue of machine translation. The purpose of the article is to define the nature of the tasks facing the editor of machine translation, and to develop general approaches to text editing. The task of the study is to analyze the journalistic text, to identify the nature of errors in the machine translation of phrases and sentences of the analyzed text, and to select methods for editing specific translation units. The objectives of the study also include the identification of typical errors of machine translation, followed by the definition of the post-editing algorithm, as well as the formulation of recommendations for machine translation editing. The study examined examples of machine translation, or rather examples of losses in translation from British English. It has been established that the most typical mistake in the translation of set phrases or set expressions is a word for word translation. The greatest difficulty for a machine translator is the translation of metaphorical expressions and phrases containing realities. At the same time, the degree of difficulty in translating a metaphor can be different. It was noted that post-editing is a mandatory element of working with the texts of machine translation. In automated translation, the machine acts as a supporter of word for word translation, and a human editor as a supporter of free translation. Post-editing of machine translation includes the ability to see logical errors and inconsistencies, the ability to select matches, to offer a descriptive translation, and, if necessary, to add a comment. During the analysis of automated translation, a certain dependence of the error rate on the characteristics of language units, namely, on the nature of lexical bindings, was revealed. In the course of the study, such correlations were established as typical characteristics of the text and the nature of automated translation errors; the nature of machine translation units and the degree of difficulty in editing. In general, it was concluded that the degree of participation of the translator or the linguist in editing the machine translation depends on the typical characteristics of the text.

APA, Harvard, Vancouver, ISO, and other styles

23

Aranberri, Nora. "What Do Professional Translators Do when Post-editing for the First Time? First Insight into the Spanish-Basque Language Pair." HERMES - Journal of Language and Communication in Business, no. 56 (October 10, 2017): 89. http://dx.doi.org/10.7146/hjlcb.v0i56.97207.

Full text

Abstract:

Machine translation post-editing is becoming commonplace and professional translators are often faced with this unknown task with little training and support. Given the different translation processes involved during post-editing, research suggests that untrained translators do not necessarily make good post-editors. Besides, the post-editing activity will be largely influenced by numerous aspects related to the technology and texts used. Training material, therefore, will need to be tailored to the particular conditions under which post-editing is bound to happen. In this work, we provide a first attempt to uncover what activity professional translators carry out when working from Spanish into Basque. Our initial analysis reveals that when working with moderate machine translation output post-editing shifts from the task of identifying and fixing errors, to that of “patchwork” where post-editors identify the machine translated elements to reuse and connect them using their own contributions. Data also reveal that they primarily focus on correcting machine translation errors but often fail to restrain themselves from editing correct structures. Both findings have clear implications for training and are a step forward in tailoring sessions specifically for language combinations of moderate quality.

APA, Harvard, Vancouver, ISO, and other styles

24

Aranberri, Nora. "What Do Professional Translators Do when Post-Editing for the First Time? First Insight into the Spanish-Basque Language Pair." HERMES - Journal of Language and Communication in Business, no. 56 (October 11, 2017): 89. http://dx.doi.org/10.7146/hjlcb.v0i56.97235.

Full text

Abstract:

Machine translation post-editing is becoming commonplace and professional translators are often faced with this unknown task with little training and support. Given the different translation processes involved during post-editing, research suggests that untrained translators do not necessarily make good post-editors. Besides, the post-editing activity will be largely influenced by numerous aspects related to the technology and texts used. Training material, therefore, will need to be tailored to the particular conditions under which post-editing is bound to happen. In this work, we provide a first attempt to uncover what activity professional translators carry out when working from Spanish into Basque. Our initial analysis reveals that when working with moderate machine translation output post-editing shifts from the task of identifying and fixing errors, to that of “patchwork” where post-editors identify the machine translated elements to reuse and connect them using their own contributions. Data also reveal that they primarily focus on correcting machine translation errors but often fail to restrain themselves from editing correct structures. Both findings have clear implications for training and are a step forward in tailoring sessions specifically for language combinations of moderate quality.

APA, Harvard, Vancouver, ISO, and other styles

25

Khromova, Anna Andreevna, and Renata Razifovna Lukmanova. "Post-editing of English to Russian machine translation: Issues, methods, and optimization." Philology. Issues of Theory and Practice 17, no. 3 (March 27, 2024): 948–56. http://dx.doi.org/10.30853/phil20240138.

Full text

Abstract:

The aim of the study is to develop recommendations for optimizing English to Russian machine translation of scientific texts in the field of natural sciences during the post-editing stage, focusing on enhancing the quality of machine translation. The article provides a systematic categorization of post-editing methods for machine translation from English to Russian of texts in the field of natural sciences, specifically neurobiology, and conducts a multi-faceted analysis of the post-editing process of machine translation. This indicates the scientific novelty of the research. Successful post-editing examples are presented, discussing its prospects for improving machine translation systems. The results revealed that during post-editing, challenges arise as online services generate incorrect syntactic structures or introduce terminological units which meanings differ from those in the original language. An important task for the post-editor is to enhance the text's comprehension, which can be achieved, for instance, through sentence reconstruction.

APA, Harvard, Vancouver, ISO, and other styles

26

O'Brien, Sharon. "An empirical investigation of temporal and technical post-editing effort." Translation and Interpreting Studies 2, no. 1 (January 1, 2007): 83–136. http://dx.doi.org/10.1075/tis.2.1.03ob.

Full text

Abstract:

This article reports on a study designed to quantify temporal and technical post-editing effort in machine translated texts. The study involved two groups of English>German translators, one instructed to post-edit a machine-translated text and the other to translate the same text from English into German. In addition, text segments containing negative translatability indicators (NTIs) were isolated in order to compare the effort involved in post-editing and translating segments with such indicators and without. Results indicate that the post-editing effort for all segments was lower than the translation effort for those segments. Additional results suggest, among other things, that the removal of NTIs may reduce relative post-editing effort overall.

APA, Harvard, Vancouver, ISO, and other styles

27

Wardana, Lalu Ali, Baharuddin Baharuddin, and Santi Farmasari. "Pre-Editing dan Post-Editing Hasil Terjemahan Mesin oleh Mahasiswa Pendidikan Bahasa Inggris Universitas Mataram." Jurnal Ilmiah Profesi Pendidikan 8, no. 3 (August 8, 2023): 1540–46. http://dx.doi.org/10.29303/jipp.v8i3.1321.

Full text

Abstract:

Artikel ini merupakan hasil penelitian yang ditujukan untuk mengukur dan mengembangkan kemampuan mahasiswa S1 Pendidikan Bahasa Inggris dalam melakukan pre-editing dan post-editing pada berbagai macam teks yang akan dimasukkan ke dalam Neural Machine Translation (NMT) dan sekaligus untuk mengukur kemampuan mahasiswa dalam melakukan (pre-post)-editing pada teks yang telah diterjemahkan oleh NMT. Objek peneltiannya adalah mahasiswa yang terdaftar dan mengikuti mata kuliah “Translation and Interpreting” pada Program Studi Pendidikan Bahasa Inggris Universitas Mataram tahun ajaran 2021/2022. Fokus artikel ini adalah kemampuan mahasiswa dalam melakukan editing terhadap hasil terjemahan NMT. Beberapa jenis teks digunakan untuk mendapatkan data yang akhirnya menunjukkan bahwa untuk setiap teks dengan ragam dan jenis yang berbeda memiliki tantangan dan kesulitan tersendiri bagi mahasiswa dalam melakukan editing. Sesuai hasil penelitiannya, artikel ini merekomendasikan bahwa mata kuliah khusus tentang pre-editing dan post-editing sangat diperlukan selain mata kuliah yang terkait penerjemahan secara langsung.

APA, Harvard, Vancouver, ISO, and other styles

28

Jia, Yanfang, and Si Lai. "Post-Editing Metaphorical Expressions: Productivity, Quality, and Strategies." Journal of Foreign Languages and Cultures 6, no. 2 (December 28, 2022): 28–43. http://dx.doi.org/10.53397/hunnu.jflc.202202004.

Full text

Abstract:

This study aims to explore the impact of neural machine translation (NMT) post-editing on metaphorical expressions from English to Chinese in terms of productivity, translation quality, and the strategies employed. To this end, a comparative study was carried out with 30 student translators who post-edited or translated a text rich in metaphors. By triangulating data from keystroke logging, retrospective protocols, questionnaires, and translation quality evaluation, it was found that: (1) processing metaphorical expressions using NMT post-editing has significantly increased the translators’ productivity compared to translating them from scratch; (2) NMT was perceived to be useful in processing metaphorical expressions and post-editing produced fewer errors in the final output than translation from scratch; (3) different strategies were used to process metaphorical expressions in post-editing and from-scratch translation due to the inherent differences in the two tasks, with “direct transfer” used most frequently in post-editing as translators usually rely on the NMT output to produce the final translation but more balanced strategies adopted in from-scratch translation as they need to seek for different solutions to rendering the metaphorical expressions; the quality of NMT output played a major role in what strategies were adopted to process the metaphorical expressions and their final product quality in post-editing, rather than the conventionality of the metaphorical expressions in the source text. Practical and research implications are discussed.

APA, Harvard, Vancouver, ISO, and other styles

29

Myung-Won Choi. "Maschinelle Übersetzung, Kontrollierte Sprache und Post-editing." Zeitschrift f？r Deutsche Sprache und Literatur ll, no. 46 (December 2009): 113–35. http://dx.doi.org/10.30947/zfdsl.2009..46.113.

Full text

APA, Harvard, Vancouver, ISO, and other styles

30

TAGHVA, KAZEM, JULIE BORSACK, BRYAN BULLARD, and ALLEN CONDIT. "POST-EDITING THROUGH APPROXIMATION AND GLOBAL CORRECTION." International Journal of Pattern Recognition and Artificial Intelligence 09, no. 06 (December 1995): 911–23. http://dx.doi.org/10.1142/s0218001495000377.

Full text

Abstract:

This paper describes a new automatic spelling correction program to deal with OCR generated errors. The method used here is based on three principles: 1. Approximate string matching between the misspellings and the terms occuring in the database as opposed to the entire dictionary 2. Local information obtained from the individual documents 3. The use of a confusion matrix, which contains information inherently specific to the nature of errors caused by the particular OCR device This system is then utilized to process approximately 10,000 pages of OCR generated documents. Among the misspellings discovered by this algorithm, about 87% were corrected.

APA, Harvard, Vancouver, ISO, and other styles

31

Ramón, Noelia, and Camino Gutiérrez-Lanza. "Translation description for assessment and post-editing." Target. International Journal of Translation Studies 30, no. 1 (February 7, 2018): 112–36. http://dx.doi.org/10.1075/target.15098.ram.

Full text

Abstract:

Abstract This paper presents a corpus-based descriptive research procedure for the identification of significant divergences between original Spanish and Spanish translated from English. When considering the language pair English-Spanish, personal pronouns seem to be good markers of significant differences (anchor phenomena), since they must obligatorily occur in English, but not in Spanish. To test this hypothesis, empirical data have been extracted from a large reference corpus in Spanish (CREA) and from an English-Spanish parallel corpus (P-ACTRES), in both cases from the fiction subcorpora. Statistically significant differences have been found in some of the uses of personal pronouns, having textual and pragmatic implications in the target texts. The aim is to use the results obtained in the case of personal pronouns, together with results from other linguistic areas, to build a semi-automated tool for the post-editing of Spanish translations of texts written originally in English.

APA, Harvard, Vancouver, ISO, and other styles

32

吕, 天一. "Post Editing Strategies in Maritime News Translation." Modern Linguistics 08, no. 02 (2020): 273–78. http://dx.doi.org/10.12677/ml.2020.82037.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Xiao, Xiao, Hui Sun, and Yanhua Wang. "Machine Translation Post-Editing Training Room Construction." Advances in Education, Humanities and Social Science Research 1, no. 3 (February 2, 2023): 284. http://dx.doi.org/10.56028/aehssr.3.1.284.

Full text

Abstract:

This paper, based on the transformation and development of applied English majors in vocational undergraduate education, is intended to construct machine translation post-editing training rooms by analyzing the language industry development status, foreign languages majors’ competence adaptability for enterprises requirements, and the connotation of machine translation post-editing training with a view to provide suggestions and references for the construction of applied English practical courses.

APA, Harvard, Vancouver, ISO, and other styles

34

O’Brien, Sharon, and Michel Simard. "Introduction to special issue on post-editing." Machine Translation 28, no. 3-4 (November 21, 2014): 159–64. http://dx.doi.org/10.1007/s10590-014-9166-8.

Full text

APA, Harvard, Vancouver, ISO, and other styles

35

Zheng, Jianwei, and Wenjun Fan. "Multivaried acceptance of post-editing in China." Pragmatics and Society 13, no. 4 (November 4, 2022): 644–62. http://dx.doi.org/10.1075/ps.19048.zhe.

Full text

Abstract:

Abstract Neural machine translation (NMT), proven to be productively and qualitatively competitive, creates great challenges and opportunities for stakeholders in both the market and the education contexts. This paper explores how English-Chinese NMT post-editing (PE) is accepted in China from the perspectives of attitude, practice, and training, based on an integrative digital survey with role-specific popup questions for translators and clients in the market setting, and for translation teachers and students in the education setting. Descriptive statistics and correlation analyses of the survey data suggest Chinese stakeholders’ generally moderate view of PE, with outsiders like clients being more optimistic about PE than are insiders like translators. In the market setting, most translators use PE to different degrees in translating primarily informative texts; here, affiliated translators report a more frequent usage, and employ more sophisticated tools than do part-time or freelance translators. Whereas translators, on the whole, fail to notify clients of their own PE usage, or to charge clients for PE and human translation (HT) differently, most clients express their willingness to accept high-quality PE output for the sake of saving cost and time. In the education setting, despite students’ concealed usage of PE to do HT assignments to varying degrees, and their wish to learn PE out of concern for their future career, PE is generally not taught in translation classrooms of Chinese universities in the form of teaching PE as a course or integrating PE content into traditional translation course.

APA, Harvard, Vancouver, ISO, and other styles

36

Guerberof-Arenas, Ana, Susana Valdez, and Aletta G. Dorst. "Does training in post-editing affect creativity?" Journal of Specialised Translation, no. 41 (January 30, 2024): 74–97. http://dx.doi.org/10.26034/cm.jostrans.2024.4712.

Full text

Abstract:

This article presents the results of an experiment with eleven students from two universities that translated and post-edited three literary texts distributed on the first and last days of their translation technology modules. The source texts were marked with units of creative potential to assess creativity in the target texts (before and after training). The texts were subsequently reviewed by an independent professional literary translator and translation trainer. The results show that there is no quantitative evidence to conclude that the training significantly affects students’ creativity. However, after the training, a change is observed both in the quantitative data and in the reflective essays, i.e. the students are more willing to try creative shifts and they feel more confident to tackle machine translation (MT) issues, while also showing a higher number of errors. Further, we observe that students have a higher degree of creativity in human translation (HT), but significantly fewer errors in post-editing (PE) overall, especially at the start of the training, than in HT.

APA, Harvard, Vancouver, ISO, and other styles

37

Rico Pérez, Celia. "Re-thinking Machine Translation Post-Editing Guidelines." Journal of Specialised Translation, no. 41 (January 30, 2024): 26–47. http://dx.doi.org/10.26034/cm.jostrans.2024.4696.

Full text

Abstract:

Machine Translation Post-Editing (MTPE) is a challenging task. It frequently creates tension between what the industry expects in terms of quality and what translators are willing to deliver as an end product. Conventional approaches to MTPE take as a point of departure the distinction between light and full MPTE, but the division gets blurred when implemented in an actual MTPE project where translators find difficulties in differentiating between essential and preferential changes. At the time MTPE guidelines were designed, the role of the human translator in the MT process was perceived as ancillary, a view inherited from the first days of MT research aiming at the so-called Fully Automatic High Quality Machine Translation (FAHQMT). My proposal challenges the traditional division of MTPE levels and presents a new way of looking at MTPE guidelines. In view of the latest developments in neural machine translation and the higher quality level of its output, it is my contention that the traditional division of MTPE levels is no longer valid. In this contribution I advance a proposal for redefining MTPE guidelines in the framework of an ecosystem specifically designed for this purpose.

APA, Harvard, Vancouver, ISO, and other styles

38

Qing, Lihua. "On the Strategies of Machine Translation Post-Editing Based on Cloud Platform." Advances in Engineering Technology Research 3, no. 1 (November 7, 2022): 11. http://dx.doi.org/10.56028/aetr.3.1.11.

Full text

Abstract:

In the era of AI, machine translation post-editing(MTPE) based on cloud platform is an important part in the translator's translation environment. This study analyzes the existing problems in machine translation, and puts forward specific post-editing strategies from the aspects of lexis, syntax, text, style and format, in order to provide some references to improve the quality of post-editing based on computer-aided translation software.

APA, Harvard, Vancouver, ISO, and other styles

39

Dai, Guangrong, and Siqi Liu. "Towards Predicting Post-editing Effort with Source Text Readability." Journal of Specialised Translation, no. 41 (January 30, 2024): 206–29. http://dx.doi.org/10.26034/cm.jostrans.2024.4723.

Full text

Abstract:

This paper investigates the impact of source text readability on the effort of post-editing English-Chinese Neural Machine Translation (NMT) output. Six readability formulas, including both traditional and newer ones, were employed to measure readability, and their predictive power towards post-editing effort was evaluated. Keystroke logging, self-report questionnaires, and retrospective protocols were applied to collect the data of post-editing for general text type from thirty-four student translators. The results reveal that: 1) readability has a significant yet weak effect on cognitive effort, while its impact on temporal and technical effort is less pronounced; 2) high NMT quality may alleviate the effect of readability; 3) readability formulas have the ability to predict post-editing effort to a certain extent, and newer formulas such as the Crowdsourced Algorithm of Reading Comprehension (CAREC) outperformed traditional formulas in most cases. Apart from readability formulas, the study shows that some fine-grained reading-related linguistic features are good predictors of post-editing time. Finally, this paper provides implications for automatic effort estimation in the translation industry.

APA, Harvard, Vancouver, ISO, and other styles

40

SHI, Qianqian. "Development of post-editing skills in machine translation." Region - Educational Research and Reviews 5, no. 3 (July 31, 2023): 125. http://dx.doi.org/10.32629/rerr.v5i3.1325.

Full text

Abstract:

As a necessary complement to machine translation, post-editing plays an increasingly vital role in the language service industry. It represents a crucial pathway for enhancing machine translation quality and serves as a significant hallmark of human-machine interactive translation. With the advancement of machine translation technology and its expanding application scope, the cultivation of post-editing skills has become a crucial component of translation education. Through well-designed training strategies, learners can enhance their post-editing abilities to meet the translation market demands of the machine translation era.

APA, Harvard, Vancouver, ISO, and other styles

41

Indarti, Dwi. "Investigating the Metacognitive Strategies During Post-Editing Translation Process: An Application of Think-Aloud Protocols (TAP)." Journal of Languages and Language Teaching 12, no. 2 (April 22, 2024): 765. http://dx.doi.org/10.33394/jollt.v12i2.10297.

Full text

Abstract:

Metacognition, the reflection on thinking processes, plays a crucial role in cognitive activities. This study delves into metacognitive strategies employed during post-editing in the translation process, particularly focusing on English-Indonesian translation through the application of think-aloud protocols (TAP). The investigation encompasses planning, monitoring, and evaluation as interconnected phases of metacognitive strategies. A qualitative case study method is employed, with a university student as the participant. Data analysis involves coding and categorizing using a thematic analysis approach, based on the metacognitive strategies framework. The findings show that the participant employes the components of planning such as evaluate the necessity of post-editing, applied knowledge on the specific post-editing cases, and identified the goal and the necessity for having specific post-editing, the components of monitoring such as using facts and instruction learned previously, making changes for a better translation product, and self-monitoring of progress, and elements of evaluating, such as deep level revising to produce better post-editing, and taking action to collect extra information. Pedagogical implications highlight the potential for enhancing learning experiences and improving translation skills through explicit instruction, modeling and systemic strategy training. The study concludes by emphasizing the importance of metacognitive flexibility, cultural influences, and adaptive strategic behavior in post-editing, shaping a roadmap for learners to navigate challenges and continually refine their approach.

APA, Harvard, Vancouver, ISO, and other styles

42

Wardana, Lalu Ali, Baharuddin Baharuddin, and Lalu Nurtaat. "Kemampuan Mahasiswa melakukan post-editing terhadap Hasil Terjemahan Machine Translation." Jurnal Ilmiah Profesi Pendidikan 7, no. 1 (February 23, 2022): 53–61. http://dx.doi.org/10.29303/jipp.v7i1.392.

Full text

Abstract:

Kemampuan mahasiswa Pendidikan Bahasa Inggris di Universitas Mataram belum terlalu mengenal adanya post-editing pada hasil terjemahan GoogleTranslate. Dalam melakukan post-editing, mahasiswa perlu dibekali dengan teori terjemahan di kelas selama perkuliahan semester ganjil 2021-2022. Meachine translation, dalam hal ini adalah Google Translate, yang terus berkembang karena komitmen klien, belum mampu secara terbuka untuk menafsirkan teks-teks logis, terutama teks-teks populer ilmiah yang dibutuhkan oleh mahasiswa, sementara kebutuhan mahasiswa untuk memahami teks di luar bahasa mereka sangatlah besar untuk pengembangan ilmu pengetahuan. Penelitian ini ditujukan untuk meneliti kemampuan mahasiswa Pendidikan Bahasa Inggris Universitas Mataram untuk melakukan post-editing pada beberapa jenis teks yang diterjemahkan dengan Google Tramslate yang biasanya menghasilkan teks yang tidak terlalu bagus. Penelitian ini dilakukan di kelas serta data-data dikumpulkan melalui penugasan yang dinilai secara wajar sambil memberikan feedback pada hasil pekerjaan mahasiswa. Dalam melakukan post-editing tersebut mahasiswa dibekali dengan kemampuan semantik dasar mahasiswa yang dikombinasikan dengan otoritas hipotesis interpretasi yang melengkapi kemampuan mahasiswa menjadi modal penting siswa dalam mengubah efek lanjutan dari hasil GoogleTranslate. Eksplorasi ini dilakukan pada mahasiswa yang mengambil mata kuliah translation and interpreting. Mata kuliah ini sengaja direncanakan sebagai studio pelatihan sehingga hipotesis dan praktik saling berhubungan untuk mendapatkan teks bahasa yang objektif dan laik. Hasil penelitian menunjukkan bahwa mahasiswa mampu melakukan post-editing terjemahan Google Translate, meskipun belum terlalu sempurna. Sebagai rekomendasi penelitian ini, bahwa perlu rekonstruksi silabus untuk matakuliah terjemahan agar mengarah kepada praktis post-editing hasil terjemahan GoogleTranslate.

APA, Harvard, Vancouver, ISO, and other styles

43

Fangfang, QIN, and XIANG Xiaomei. "On the Translation Strategies of Human-computer Interaction Based on Machine Translation." Education, Language and Sociology Research 3, no. 4 (October 20, 2022): p43. http://dx.doi.org/10.22158/elsr.v3n4p43.

Full text

Abstract:

With the rapid development of language service industry and artificial intelligence technology, machine translation plays a more prominent role in the translation industry. Human-computer interaction translation greatly improves the speed and quality of translation, and pre-translation editing and post-translation editing are two important links and manifestations in human-computer interaction collaborative translation. On the basis of summarizing machine translation problems, this paper proposes translation strategies including replacing well-translated terms in advance, rewriting, addition, omission, and shift via pre-editing and post-editing, which greatly improves the quality of machine translation.

APA, Harvard, Vancouver, ISO, and other styles

44

Béchara, Hannah, Constantin Orăsan, Carla Parra Escartín, Marcos Zampieri, and William Lowe. "The Role of Machine Translation Quality Estimation in the Post-Editing Workflow." Informatics 8, no. 3 (September 14, 2021): 61. http://dx.doi.org/10.3390/informatics8030061.

Full text

Abstract:

As Machine Translation (MT) becomes increasingly ubiquitous, so does its use in professional translation workflows. However, its proliferation in the translation industry has brought about new challenges in the field of Post-Editing (PE). We are now faced with a need to find effective tools to assess the quality of MT systems to avoid underpayments and mistrust by professional translators. In this scenario, one promising field of study is MT Quality Estimation (MTQE), as this aims to determine the quality of an automatic translation and, indirectly, its degree of post-editing difficulty. However, its impact on the translation workflows and the translators’ cognitive load is still to be fully explored. We report on the results of an impact study engaging professional translators in PE tasks using MTQE. To assess the translators’ cognitive load we measure their productivity both in terms of time and effort (keystrokes) in three different scenarios: translating from scratch, post-editing without using MTQE, and post-editing using MTQE. Our results show that good MTQE information can improve post-editing efficiency and decrease the cognitive load on translators. This is especially true for cases with low MT quality.

APA, Harvard, Vancouver, ISO, and other styles

45

Ma, Suyu, Chunyang Chen, Hourieh Khalajzadeh, and John Grundy. "Latexify Math: Mathematical Formula Markup Revision to Assist Collaborative Editing in Math Q&A Sites." Proceedings of the ACM on Human-Computer Interaction 5, CSCW2 (October 13, 2021): 1–24. http://dx.doi.org/10.1145/3479547.

Full text

Abstract:

Collaborative editing questions and answers plays an important role in quality control of Mathematics StackExchange which is a math Q&A Site. Our study of post edits in Mathematics Stack Exchange shows that there is a large number of math-related edits about latexifying formulas, revising LaTeX and converting the blurred math formula screenshots to LaTeX sequence. Despite its importance, manually editing one math-related post especially those with complex mathematical formulas is time-consuming and error-prone even for experienced users. To assist post owners and editors to do this editing, we have developed an edit-assistance tool, MathLatexEdit for formula latexification, LaTeX revision and screenshot transcription. We formulate this formula editing task as a translation problem, in which an original post is translated to a revised post. MathLatexEdit implements a deep learning based approach including two encoder-decoder models for textual and visual LaTeX edit recommendation with math-specific inference. The two models are trained on large-scale historical original-edited post pairs and synthesized screenshot-formula pairs. Our evaluation of MathLatexEdit not only demonstrates the accuracy of our model, but also the usefulness of MathLatexEdit in editing real-world posts which are accepted in Mathematics Stack Exchange.

APA, Harvard, Vancouver, ISO, and other styles

46

Nakamura, Shingo, Emi Inada, Issei Saitoh, and Masahiro Sato. "Recent Genome-Editing Approaches toward Post-Implanted Fetuses in Mice." BioTech 12, no. 2 (May 11, 2023): 37. http://dx.doi.org/10.3390/biotech12020037.

Full text

Abstract:

Genome editing, as exemplified by the CRISPR/Cas9 system, has recently been employed to effectively generate genetically modified animals and cells for the purpose of gene function analysis and disease model creation. There are at least four ways to induce genome editing in individuals: the first is to perform genome editing at the early preimplantation stage, such as fertilized eggs (zygotes), for the creation of whole genetically modified animals; the second is at post-implanted stages, as exemplified by the mid-gestational stages (E9 to E15), for targeting specific cell populations through in utero injection of viral vectors carrying genome-editing components or that of nonviral vectors carrying genome-editing components and subsequent in utero electroporation; the third is at the mid-gestational stages, as exemplified by tail-vein injection of genome-editing components into the pregnant females through which the genome-editing components can be transmitted to fetal cells via a placenta-blood barrier; and the last is at the newborn or adult stage, as exemplified by facial or tail-vein injection of genome-editing components. Here, we focus on the second and third approaches and will review the latest techniques for various methods concerning gene editing in developing fetuses.

APA, Harvard, Vancouver, ISO, and other styles

47

Kumari, Chanchal, Megha Sharma, Vinay Kumar, Rajnish Sharma, Vinay Kumar, Parul Sharma, Pankaj Kumar, and Mohammad Irfan. "Genome Editing Technology for Genetic Amelioration of Fruits and Vegetables for Alleviating Post-Harvest Loss." Bioengineering 9, no. 4 (April 18, 2022): 176. http://dx.doi.org/10.3390/bioengineering9040176.

Full text

Abstract:

Food security and crop production are challenged worldwide due to overpopulation, changing environmental conditions, crop establishment failure, and various kinds of post-harvest losses. The demand for high-quality foods with improved nutritional quality is also growing day by day. Therefore, production of high-quality produce and reducing post-harvest losses of produce, particularly of perishable fruits and vegetables, are vital. For many decades, attempts have been made to improve the post-harvest quality traits of horticultural crops. Recently, modern genetic tools such as genome editing emerged as a new approach to manage and overcome post-harvest effectively and efficiently. The different genome editing tools including ZFNs, TALENs, and CRISPR/Cas9 system effectively introduce mutations (In Dels) in many horticultural crops to address and resolve the issues associated with post-harvest storage quality. Henceforth, we provide a broad review of genome editing applications in horticulture crops to improve post-harvest stability traits such as shelf life, texture, and resistance to pathogens without compromising nutritional value. Moreover, major roadblocks, challenges, and their possible solutions for employing genome editing tools are also discussed.

APA, Harvard, Vancouver, ISO, and other styles

48

Saad Mudheher Al Sammarraie, Huda, and Mozhgan Ghassemiazghandi. "Enhancing Post-Editing Machine Translation Skills Among Iraqi Undergraduate Students." Arab World English Journal For Translation and Literary Studies 8, no. 2 (May 24, 2024): 165–82. http://dx.doi.org/10.24093/awejtls/vol8no2.12.

Full text

Abstract:

Post-editing machine translation often results in discrepancies between industry expectations and the actual quality of the final product. Despite the usually, low-quality outcomes associated with machine translation, it remains underutilized, even when there are opportunities for improvement through post-editing jobs. This study focuses on the impact of technology-assisted training on English proficiency among students. It investigates a standard error observed among Iraqi students during the post-editing of machine translations using Google Translate deciding whether to edit the machine translation output or to translate from scratch and understand the source text. This research involved 20 undergraduates from Al-Mustansiriyah University and employed a mixed methods approach, collecting data through an online questionnaire completed by students in the undergraduate translation program. The findings indicate a significant improvement in the frequency of post-editing skills among Iraqi students, serving as a distinguishing factor between the two groups. It also highlighted differences in translation abilities among students in Iraqi higher education, with notable improvements observed in the experimental group. In summary, this study supports previous research from the last five years, indicating a more favourable attitude toward machine translation and suggesting that post-editing is considered an essential sub-competency in translation education.

APA, Harvard, Vancouver, ISO, and other styles

49

Alvarez-Vidal, Sergi, Antoni Oliver, and Toni Badia. "Post-editing for Professional Translators: Cheer or Fear?" Tradumàtica: tecnologies de la traducció, no. 18 (December 30, 2020): 49. http://dx.doi.org/10.5565/rev/tradumatica.275.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Shin, Jaehun, Youngkil Kim, and Jong-hyeok Lee. "Transformer-based Automatic Post-Editing for Machine Translation." KIISE Transactions on Computing Practices 25, no. 1 (January 31, 2019): 64–69. http://dx.doi.org/10.5626/ktcp.2019.25.1.64.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Post-editing'

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