Universität Wien

340217 VU Basics in Machine Translation (2024S)

5.00 ECTS (3.00 SWS), SPL 34 - Translationswissenschaft
Prüfungsimmanente Lehrveranstaltung

An/Abmeldung

Hinweis: Ihr Anmeldezeitpunkt innerhalb der Frist hat keine Auswirkungen auf die Platzvergabe (kein "first come, first served").

Details

max. 40 Teilnehmer*innen
Sprache: Englisch

Lehrende

Termine (iCal) - nächster Termin ist mit N markiert

  • Montag 11.03. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 18.03. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 08.04. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 15.04. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 29.04. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 06.05. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 13.05. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 27.05. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 03.06. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 10.06. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG
  • Montag 17.06. 16:45 - 19:00 Medienlabor II ZfT Gymnasiumstraße 50 4.OG

Information

Ziele, Inhalte und Methode der Lehrveranstaltung

- This course will be taught in person in the ZTW computer lab, without a hybrid or online option -

Goals:
Students will acquire practical machine translation (MT), customisation, annotation, and post-editing expertise within computer-assisted translation (CAT) tools.
Using state-of-the-art technologies, students will learn to fine-tune pre-trained MT models, evaluate them using automatic and manual metrics, integrate MT into CAT tools, annotate their output using standard industry annotation frameworks, and post-edit MT output according to ISO standards.

Content:
- Rule-Based (RBMT), Statistical (SMT), and neural machine translation (NMT)
- NMT encoder decoder architecture
- NMT transformer architecture and fine-tuning pre-trained models
- MT automatic evaluation metrics and manual annotation of error typologies - Post-editing machine translation (PEMT) standards and best practices

Didactic approach:

This course will be team-taught, with each team member focusing on one or more relevant topics.
Students will need to complete practical assignments involving a 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 in English, with some opportunities for using other languages to complete the coursework.

Art der Leistungskontrolle und erlaubte Hilfsmittel

Continuous evaluation:
- attendance, weekly reflections, and in-class participation count for 20% of the mark.
- NMT code base 40%
- NMT fine-tuning, annotation, and post-editing task deliverables - 20% of the mark.
- NMT course report - 20% of the mark.

All media and tools are allowed, but their use needs to be referenced. Furthermore, if using AI Tools such as ChatGPT you also need to provide, in a footnote, the prompt used. Generally, we follow the principles described here: https://libguides.brown.edu/c.php?g=1338928&p=9868287

Mindestanforderungen und Beurteilungsmaßstab

In order to pass this module, a student needs to reach the threshold of 4.

MT marking map
excellent - sehr gut (1)
good - gut (2)
average - befriedigend (3)
sufficient - genügend (4)
insufficient - nicht genügend (5)

Prüfungsstoff

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

Literatur

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
- Moniz, H., & Parra Escartín, C. (Eds.). (2023). Towards Responsible Machine Translation: Ethical and Legal Considerations in Machine Translation (Vol. 4). Springer International Publishing. https://doi.org/10.1007/978-3-031-14689-3
- Pilehvar, Mohammad Taher and José Camacho-Collados. 2020. Embeddings in Natural Language Processing: Theory and Advances in Vector Representations of Meaning. Synthesis Lectures on Human Language Technologies (http://josecamachocollados.com/book_embNLP_draft.pdf).
- 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:

- The Illustrated Word2vec. https://jalammar.github.io/illustrated-word2vec/
- Visualizing A Neural Machine Translation Model (Mechanics of Seq2seq Models With Attention). https://jalammar.github.io/visualizing-neural-machine-translation-mechanics-of-seq2seq-models-with-attention/
- 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.
- 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.

Zuordnung im Vorlesungsverzeichnis

Letzte Änderung: Mi 28.02.2024 11:47