Universität Wien
Warning! The directory is not yet complete and will be amended until the beginning of the term.

340370 UE Machine translation (2023W)

3.00 ECTS (2.00 SWS), SPL 34 - Translationswissenschaft
Continuous assessment of course work

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

max. 25 participants
Language: German, English

Lecturers

Classes (iCal) - next class is marked with N

  • Friday 12.01. 09:45 - 11:15 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Friday 12.01. 11:30 - 13:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Friday 19.01. 09:45 - 11:15 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Friday 19.01. 11:30 - 13:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Friday 02.02. 09:45 - 11:15 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Friday 02.02. 11:30 - 13:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Thursday 08.02. 09:45 - 11:15 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Thursday 08.02. 11:30 - 13:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Friday 09.02. 09:45 - 11:15 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Friday 09.02. 11:30 - 13:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Saturday 10.02. 09:45 - 11:15 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Saturday 10.02. 11:30 - 13:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG

Information

Aims, contents and method of the course

- This course will be taught in person in the ZTW computer lab, without a hybrid or online option -
Goals:
Students will acquire hands-on computer-assisted translation (CAT) tool knowledge alongside machine translation (MT) integration, customisation, annotation, and post-editing expertise.
Using state-of-the-art technologies, students will learn to fine-tune and adapt pre-trained MT models, evaluate them using automatic and manual metrics, integrate them into a popular CAT tool, annotate their output using popular industry annotation frameworks, and post-edit MT output according to ISO standards. Students are also encouraged to explore the use of modern generative large language models for translation and other tasks.

Content:
- Computer-Assisted Translation (CAT) tools
- Rule-based (RBMT), statistical (SMT) and deep learning-based machine translation (NMT and generative language models): brief overview and current applications
- NMT architectures and fine-tuning pre-trained models
- MT evaluation metrics and annotation tools and techniques
- MT in professional workflows
- MT in the language industry
- Controlled language; pre-editing
- Post-editing machine translation (PEMT) standards and best practices
- Ethics of using MT and impact of MT on freelance linguists

Didactic approach:
To the students, this course is likely to appear as a simulated, technology-intensive internship with a language service provider (LSP).
Students will need to complete assignments involving a wide range of technologies for fine-tuning, integrating, evaluating, and improving MT output. Students will also gain experience of post-editing MT output according to ISO standards. The course will be taught mainly in German, with some opportunities for interaction in English. Based on student request, an automatic, machine-generated translation into other languages of the recording of the sessions can be provided. The recording does not replace the need for physical presence during the exercise.

Assessment and permitted materials

Continuous evaluation:
- attendance, exercise reports and in-class participation count for 30% of the mark.
- MT fine-tuning task deliverables and seminar paper - 35% of the mark.
- MT evaluation, annotation and post-editing task deliverables and seminar paper - 35% of the mark.

Minimum requirements and assessment criteria

MT UE pass markIn order to pass this module, a student needs to reach the threshold of 4.
MT UE marking map
excellent - sehr gut (1)
good - gut (2)
average - befriedigend (3)
sufficient - genügend (4)
insufficient - nicht genügend (5)

Examination topics

- MT fine-tuning
- MT evaluation
- MT post-editing

Reading list

Core texts:
- Kenny, Dorothy. 2022. Machine translation for everyone: Empowering users in the age of artificial intelligence. (Translation and Multilingual Natural Language Processing 18). Berlin: Language Science Press. DOI: 10.5281/zenodo.6653406 (url: https://langsci-press.org/catalog/book/342)
- Koehn, P. 2020. Neural Machine Translation. Cambridge University Press
- BS EN ISO 17100:2015: Translation Services. Requirements for translation services
- ISO/DIS 18587 Translation services - Post-editing of machine translation output – Requirements

Additional recommended resources:
- Alammar, J. 2018a. The Illustrated Transformer. Retrieved from https://jalammar.github.io/illustrated-transformer/ (Accessed on: February 1, 2020)
- Alammar, J. 2018b. Visualizing A Neural Machine Translation Model (Mechanics of Seq2seq Models With Attention). Retrieved from https://jalammar.github.io/visualizing-neural-machine-translation-mechanics-of-seq2seq-models-with-attention/ (Accessed on: February 1, 2020)
- Bird, S., Klein, E., & Loper, E. 2009. NLTK Book. Natural Language Processing with Python. O’Reilly Media Inc. Retrieved from http://www.nltk.org/book/ (Accessed on: September 14, 2019)
- Bawden, R. 2018. Going beyond the sentence : Contextual Machine Translation of Dialogue. Université Paris-Saclay. Retrieved from https://tel.archives-ouvertes.fr/tel-02004683 (Accessed on: March 18, 2020)
- Brown et al. 2020. Language Models are Few-Shot Learners. Retrieved from https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
-Deutscher Terminologie-Tag e.V. (Hg.). 2014. Terminology Work: Best Practices 2.0. Cologne: Dt. Terminologie-Tag.
- Globally Speaking: A podcast for and by localization professionals. https://www.globallyspeakingradio.com/
- Carstensen, K-U. 2017. Sprachtechnologie - Ein Überblick. http://kai-uwe-carstensen.de/
Publikationen/Sprachtechnologie.pdf
- Chan, Sin-Wai. Ed. 2015. Routledge encyclopedia of translation technology Abingdon, Oxon : Routledge.
- Depraetere, I. Ed. 2011. Perspectives on translation quality. Berlin: de Gruyter Mouton
- Hausser, Roland. 2000. Grundlagen der Computerlinguistik - Mensch-Maschine-Kommunikation in natürlicher Sprache (mit 772 – Übungen). Springer.
- Kockaert, H. J. and Steurs, F. Eds. 2015. Handbook of terminology. Amsterdam; Philadelphia: John Benjamins Publishing Company.
- Koehn, P. 2010. Statistical Machine Translation. Cambridge: Cambridge University Press.
- Lang, C. 2020. Neural Machine Translation - How machines learn to translate patent language - An overview, evaluation and tutorial. Master’s thesis, University of Vienna.
- Lo Presti, R. 2016. Menschliche und automatische Evaluation von Übersetzungen von Fachtexten in Google Translate. Master’s thesis, University of Vienna.
- Luong, M.-T. 2016. Neural Machine Translation - A Dissertation. Standford University. Retrieved from https://github.com/lmthang/thesis
- Munday, J. 2012. Evaluation in translation: critical points of translator decision-making: Routledge.
- O'Hagan, M. Ed. 2019. The Routledge Handbook of Translation and Technology. Abingdon: Routledge
- Waibel, A. 2015. Sprachbarrieren durchbrechen: Traum oder Wirklichkeit? Nova Acta Leopoldina NF 122, Nr. 410, 101–123. https://isl.anthropomatik.kit.edu/downloads/NAL_Bd122_Nr410_101-124_Waibel_low_res.pdf
- Wright, S. E. and Budin, G. 1997/2001. The Handbook of Terminology Management. Two volumes. Amsterdam/Philadelphia: John Benjamins Publishing Company.

Association in the course directory

Last modified: Fr 29.12.2023 10:06