IT skills are central to the translator's work, and the aim of this module is to demonstrate how the efficiency of the translation process and the translator's marketability can be improved by an enhanced knowledge of the relevant technological tools. Theoretical knowledge is coupled with hand-on-training and students develop transferable skills through "hands-on" sessions that emphasise the "real world" translation environment. The main focus of the module will be on Computer-assisted tools (CAT-tools, RWS Trados, Phrase, BWX, XTM κ.ά.), including cloud-based tools and open-source tools. An introduction to Machine Translation (MT) (with an emphasis on Neural Machine Translation and Generative AI) and MT evaluation https://mateo.ivdnt.org/Evaluate, including human and automatic evaluation metrics is included in the module. Extensive post-editing practice is offered.
Upon completion of the module, students will be able to:
Week 1: Preview of the course. Translation and its compatibility with technology. Machine translation: introduction to machine translation, historical background, ethical and moral issues.
Week 2: Types and approaches to machine translation (statistical, neural, etc.) and how to train them.
Week 3: Evaluation of machine translation systems. Automatic metrics and quality estimation. Practical application of metrics, https://mateo.ivdnt.org/Evaluate.
Week 4: Human evaluation. Adequacy/fluency, ranking and error analysis (MQM/DQF typology). Pre-editing and post-editing of machine translated text: introduction.
Week 5: Techniques and types of post-editing. Types and techniques of editing and proofreading of machine-translated text: practical exercises. Editing of machine-translated text: practice and error categorisation.
Week 6: Introduction to CAT tools. BWX I: Introduction to the tool. Managing translation memories and terminology bases, importing and exporting files, text alignment, using machine translation and the built-in version of ChatGPT.
Week 7: BWX II: Translating a Word file. Practical exercise and discussion on the use of AI in the process.
Week 8: Phrase I: Presentation. Managing translation memories and terminology bases, importing and exporting tmx and tbx files, text alignment.
Week 9: Phrase II: Translation of a Word file and translation of different file formats (PDF, Excel, SRT, XML, etc.).
Week 10: Multiterm: searching a terminology base, creating a terminology base by converting a ready-made file/entirely new base, adding entries to a terminology base, exporting terminology. Trados Studio I: initial start-up, overview of the user interface, personal settings.
Week 11: Trados Studio I: Translation of a Word file (auto-propagation, fuzzy match, exact match, context match, tags, concordance search, spell check, quality assurance check).
Week 12: Trados Studio II: Translation of different file formats (PDF, Excel, SRT, XML, etc.). Basic keyboard shortcuts. Management of translation memories, text alignment, creation of autosuggest dictionaries.
Week 13: Trados Studio III: Using the built-in version of ChatGPT.
Allen J (2003) Post-editing. Computers and Translation. A Translator’s Guide, edited by Harold Somers, 297–317. John Benjamins, Amsterdam.
Bojar O, Chatterjee R, Federmann C, Graham Y, Haddow B, Huck M et al. (2016) Findings of the 2016 conference on Machine Translation. In: Proceedings of the First Conference on Machine Translation: Shared Task Papers (WMT), Vol. 2, pp. 131–198.
Bowker L (2002) Computer Aided Translation Technology: A Practical Introduction. Ottawa: Ottawa University Press.
Carl M, Buch-Kromann M (2010) Correlating Translation Product and Translation Process Data of Professional and Student Translators. In Proceedings of EAMT, Saint-Raphael, France.
Castilho S, Moorkens J, Gaspari F, Calixto I, Tinsley J, Way A (2017a) Is Neural Machine Translation the New State of the Art? The Prague Bulletin of Mathematical Linguistics, 108(1): 109–120
Castilho S, Moorkens J, Gaspari F, Sennrich R, Sosoni V, Georgakopoulou Y, Lohar P, Way A, Miceli Barone A, Gialama M (2017b) A Comparative quality evaluation of PBSMT and NMT using professional translators. Proceedings of Machine Translation Summit XVI. Nagoya, Japan.
de Almeida G (2013) Translating the post-editor: An investigation of post-editing changes and correlations with professional experience. PhD Thesis, Dublin City University
Depraetere I (2010) What Counts as Useful Advice in a University Post-editing Training Context? Report on a case study. Proceedings of the 14th Annual EAMT Conference. St. Raphael, May 27-28. Accessed June 2013. http://www.mt-archive.info/EAMT-2010-Depraetere-2.pdf.
Doherty, S (2016) The Impact of Translation Technologies on the Process and Product of Translation. International Journal of Communication 10, 947–969.
García, I. 2010. Is Machine Translation Ready Yet?. Target 22(1):7–21. John Benjamins, Amsterdam.
Gaspari F, Toral A, Kumar Naskar S, Groves D, Way, A (2014) Perception vs reality: Measuring machine translation post-editing productivity. Paper presented to the 3rd workshop on post-editing technology and practice (WPTP-3), within the 11th biennial conference of the Association Human Factors in Computing Systems (CHI). http://vis.stanford.edu/papers/post-editing
Goutsos D, Fragkaki G (2015) Introduction to Corpus Linguistics [in Greek]. Athens: Kallipos. https://repository.kallipos.gr/handle/11419/1932
Göpferich S, Gerrit BH, Friederike P, Stadlober J (2011) Exploring Translation Competence Acquisition: Criteria of Analysis Put to the Test. In Cognitive Explorations of Translation, edited by Sharon O’Brien, 57-86. Continuum Studies in Translation. London: Continuum
Hvelplund KT (2011) Allocation of cognitive resources in translation: An eye-tracking and key-logging study. PhD thesis, Copenhagen Business School
Jia Y, Carl M, Wang X (2019) How does the post-editing of Neural Machine Translation compare with from-scratch translation? A product and process study, Jostrans: The Journal of Specialised Translation, 31: 60-86
Koponen M (2012) Comparing human perceptions of post-editing effort with post-editing operations. Proceedings of the 7th workshop on statistical machine translation. Montreal, Canada
Koponen M (2016a) Is machine translation post-editing worth the effort? A survey of research into post-editing and effort. Jostrans: The Journal of Specialised Translation, 25: 131-148
Koponen M (2016b) Machine translation post-editing and effort: Empirical Studies on the post-editing effort. PhD Thesis, University of Helsinki
Krings Η (2001) Repairing texts: Empirical investigations of machine translation post-editing processes. Kent State University Press
Lommel A R, DePalma DA (2016) Europe’s leading role in Machine Translation: How Europe is driving the shift to MT. Technical report. Common Sense Advisory, Boston
Mesa-Lao B (2014) Gaze behaviour on source texts: An exploratory study comparing translation and post-editing. In O'Brien S, Balling LW, Carl M, Simard M, Specia L (eds) Post-editing of machine translation. Cambridge Scholars Publishing, Newcastle
Mitchell L (2015) Community post-editing of machine-translated user-generated content. PhD thesis. Dublin City University.
Moorkens J, Castilho S, Gaspari F, and Doherty S (2018) Translation Quality Assessment: From Principles to Practice. Springer, Heidelberg.
Moorkens J (2018) Eye tracking as a measure of cognitive effort for post-editing of machine translation. In: Calum W, Federici FM (eds) Eye tracking and multidisciplinary studies on translation. John Benjamins, Amsterdam, pp 55-69
Moorkens J, O’Brien S (2015) Post-editing evaluations: Trade-offs between novice and professional participants. In: Durgar El‐Kahlout İ, Özkan M, Sánchez‐Martínez F, Ramírez‐Sánchez G, Hollowood F, Way A (eds) Proceedings of European Association for Machine Translation (EAMT) 2015, Antalya, pp 75–81
O'Brien S (2012) Translation and human-computer interaction. Translation Spaces, 1 (1), 101-122
O’Brien S, Simard M (2014) Introduction to special issue on postediting. Machine Translation 28(3), 159–164
O'Brien S, Balling WL, Carl M, Simard M, Specia L (eds) (2014) Post-editing of machine translation: Processes and applications. Cambridge Scholars Publishing, Newcastle
Popović M (2017) Comparing Language Related Issues for NMT and PBMT between German and English. The Prague Bulletin of Mathematical Linguistics, 108(1): 209–220
Quah K C (2006) Translation and Technology. New York: Palgrave Macmillan
Stasimioti M, Sosoni V (2020) Translation vs Post-editing of NMT Output: Measuring effort in the English-Greek language pair. Proceeding of 1st Workshop on Post-Editing in Modern-Day Translation, AMTA 2020, 6 October 2020, Online Conference
Stasimioti M, Sosoni V, Kermanidis KL, Mouratidis, D (2020) Machine Translation Quality: A comparative evaluation of SMT, NMT and tailored-NMT outputs. Proceedings of the 22nd Annual Conference of the European Association for Machine Translation. Lisbon November 2020, 441-450.https://www.aclweb.org/anthology/2020.eamt-1.47.pdf
Stasimioti M & Sosoni V (2019) MT output and post-editing effort: Insights from a comparative analysis of SMT and NMT output for the English to Greek language pair and implications for the training of post-editors. In C. Szabó & R. Besznyák (eds) (2019) Teaching Specialised Translation and Interpreting in a Digital Age - Fit-For-Market Technologies, Schemes and Initiatives. Wilmington: Vernon Press
Stasimioti M & Sosoni V (2019) Undergraduate translation students’ performance and attitude vis-à-vis Machine Translation and Post-editing: Does training playing a role? Conference Proceedings Translating and the Computer 41, London 21-22 November 2019. https://www.asling.org/tc41/?page_id=2078
Toral A, Sánchez-Cartagena VM (2017) A Multifaceted Evaluation of Neural versus Phrase Based Machine Translation for 9 Language Directions. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Vol. 1, pp. 1063-1073
Toral A, Way A (2018) “What level of quality can Neural Machine Translation attain on literary text?” In Translation Quality Assessment: From Principles to Practice, edited by J. Moorkens, S Castilho, F Gaspari, and S Doherty, 263-287, Springer, Heidelberg.
Toral A, Wieling M, and Way A (2018) “Post-editing Effort of a Novel with Statistical and Neural Machine Translation”. Frontiers in Digital Humanities 5:9.
Vieira LN, Alonso E, Bywood L (2019) Introduction: Post-editing in practice – Process, product and networks. Jostrans: The Journal of Specialised Translation, 31: 2-13.
Wagner E (1985) Post-editing Systran – A Challenge for Commission Translators. Terminologie et Traduction, (3).
Yamada M (2015) Can college students be post-editors? An investigation into employing language learners in machine translation plus post-editing settings. Machine Translation, 29: 49-67.
Yamada M (2019) The impact of Google Neural Machine Translation on Post-editing by student translators, Jostrans: The Journal of Specialised Translation, 31: 87-106.
Zhechev V (2014) Analysing the post-editing of machine translation at autodesk. In: O’Brien S, Balling LW, Carl M, Simard M, Specia L (eds) (2014) Postediting of machine translation: Processes and application. Cambridge Scholars, pp 2–13.
The lesson has a hybrid lecture-workshop format. It is largely based on the interaction with students and classroom discussion. Hands-on-sessions focus on practical aspects of the issues covered and described during the lectures. Invited speakers from the industry cover all the latest technological developments.
Students have hands-on sessions on CAT-tools (RWS Trados Studio, Multiterm, Phrase, BWX) and MT systems, and automatic metrics https://mateo.ivdnt.org/Evaluate. The material is made available through the Open e-class platform.
A final written exam and a final written assignment are used to assess the students. It consists of using a CAT tool, post-editing of MT output, as well as error analysis/annotation, accuracy and fluency assessment and commentary of the procedure. Weekly individual or group exercises or assignments are also assigned to students as a continuous form of assessment.
