Description and contextualization of the subject

In this course the existing machine translation (MT) paradigms will be presented and the student will have the opportunity to practice with real MT systems. In addition, the different possibilities that exist for extracting and using multilingual information from both parallel and monolingual corpus will also be analysed.

Learning outcomes of the subject

Know the different Machine Translation paradigms proposed.

Understand the Machine Translation related scientific papers: the different techniques and the evaluation.

Learn to train the state of the art Machine Translation systems.

Identify the multilingual information present in the data and how it can be used in the design of multilingual tools.

Identify use cases where Machine Translation can lead an improvement in the results.

Ordinary call: orientations and renunciation

The evaluation will consist of two sections: Tasks (85%) and class attendance and participation (15%).

- Tasks: The students will be evaluated through activities proposed during the module. Part of the class time will be dedicated to carry out such tasks, which can be elaborated outside class time.

- Attendance and participation. It will be necessary to attend 80% of the classes and actively participate in class discussions and activities.

Extraordinary call: orientations and renunciation

Students will be able to resubmit the tasks assigned during the module, which will be re-assessed to increase the score related to the Tasks section (85%). The score for the attendance and participation section (15%) will be the same as those obtained in the ordinary call.

Temary

1.- Introduction

2.- Evaluation of Machine Translation

3.- Machine Translation Methods

4.- Multilingualism

Bibliography

Basic bibliography

Mikel Artetxe, Gorka Labaka, Eneko Agirre. 2018. A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers), pages 789¿798. Melbourne, Australia

Mikel Artetxe, Gorka Labaka, Eneko Agirre. 2019. An Effective Approach to Unsupervised Machine Translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 194¿203. Florence, Italy

Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio. Neural Machine Translation by Jointly Learning to Align and Translate. arXiv preprint arXiv:1409.0473

Philipp Koehn. 2010. Statistical Machine Translation. Cambridge University Press

Kishore Papineni, Salim Roukos, Todd Ward, Wei-Jing Zhu. 2002. BLEU: a MethodforAutomaticEvaluationofMachineTranslation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), pages 311-318. Philadelphia

Matthew Snover, Bonnie Dorr, Richard Schwartz, Linnea Micciulla, John Makhoul. 2006. A Study of Translation Edit Rate with Targeted Human Annotation. In Proceedings of Association for Machine Translation in the Americas

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin. Attention Is All You Need. Advances in neural information processing systems, 5998-6008.