Enabling Outbound Machine Translation

• Thesis title in Czech: Podpora psaní textu v neznámém jazyce
• Thesis title in English: Enabling Outbound Machine Translation
• English key words: quality estimation, machine translation, outbound translation, natural language processing, web application
• Academic year of topic announcement: 2019/2020
• Thesis type: Bachelor's thesis
• Thesis language: angličtina
• Department: Institute of Formal and Applied Linguistics (32-UFAL)
• Supervisor: doc. RNDr. Ondřej Bojar, Ph.D.
• Author: Bc. Vilém Zouhar - assigned and confirmed by the Study Dept.
• Date of registration: 06.12.2019
• Date of assignment: 06.12.2019
• Confirmed by Study dept. on: 12.12.2019
• Date and time of defence: 07.07.2020 09:00
• Date of electronic submission: 02.06.2020
• Date of submission of printed version: 04.06.2020
• Date of proceeded defence: 07.07.2020
• Opponents: Mgr. Martin Popel, Ph.D.

Guidelines

Google Translate, Bing Translator and other alternatives for machine translation (MT) are widely used for reading texts in foreign languages. Producing texts using MT is more problematic because most users would not have enough confidence in the MT system to use it for official communication, such as emails, reports or web forms.

The goal of this thesis is to implement a proof of concept of a web user interface which combines online machine translation together additional systems for increasing users' confidence in the MT output. Such systems include backward translation or automatic quality estimation.

This work should be complemented by a small experiment on users to empirically assess the usefulness of the system and provide insight into the strategies users take when translating text into a language they do not speak.

References

Erick Fonseca, Lisa Yankovskaya, André F. T. Martins, Mark Fishel, and Christian Federmann. Findings of the wmt 2019 shared tasks on quality estimation. In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pages 1–12, Florence, Italy, August 2019. Association for Computational Linguistics.

Nicola Ueffing and Hermann Ney. Word-level confidence estimation for machine translation. Computational Linguistics, 33(1):9–40, 2007.

Lucia Specia, Gustavo Paetzold, and Carolina Scarton. Multi-level translation quality prediction with QuEst++. In Proceedings of ACL-IJCNLP 2015 System Demonstrations, pages 115–120, Beijing, China, July 2015. Association for Computational Linguistics and The Asian Federation of Natural Language Processing.

Julia Ive, Frédéric Blain, and Lucia Specia. deepQuest: A framework for neural-based quality estimation. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3146–3157, Santa Fe, New Mexico, USA, August 2018. Association for Computational Linguistics.

Fabio Kepler, Jonay Trénous, Marcos Treviso, Miguel Vera, and André F. T. Martins. OpenKiwi: An open source framework for quality estimation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 117–122, Florence, Italy, July 2019. Association for Computational Linguistics.

Bojar Ondřej. Čeština a strojový překlad. ÚFAL, Praha, Czechia, ISBN 978-80-904571-4-0, 168 pp. 2012. http://ufal.mff.cuni.cz/books_bojar_2012.html