Abstract
While recent advances in deep learning led to significant improvements in machine translation, neural machine translation is often still not able to continuously adapt to the environment. For humans, as well as for machine translation, bilingual dictionaries are a promising knowledge source to continuously integrate new knowledge. However, their exploitation poses several challenges: The system needs to be able to perform one-shot learning as well as model the morphology of source and target language.In this work, we proposed an evaluation framework to assess the ability of neural machine translation to continuously learn new phrases. We integrate one-shot learning methods for neural machine translation with different word representations and show that it is important to address both in order to successfully make use of bilingual dictionaries. By addressing both challenges we are able to improve the ability to translate new, rare words and phrases from 30% to up to 70%. The correct lemma is even generated by more than 90%.
Original language | English |
---|---|
Title of host publication | 16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021) |
Publisher | Association for Computational Linguistics |
Pages | 830-840 |
Number of pages | 11 |
ISBN (Print) | 9781954085022 |
Publication status | Published - 2021 |
Event | 16th Conference of the European Chapter of the Association for Computational Linguistics: Tutorials - Online, Unknown Duration: 19 Apr 2021 → 23 Apr 2021 Conference number: 16 https://2021.eacl.org/#:~:text=EACL%202021%20will%20be%20held,recreate%20a%20true%20conference%20experience. https://2021.eacl.org/#:~:text=Welcome%20to%20the%2016th%20conference,will%20be%20held%20entirely%20online. |
Conference
Conference | 16th Conference of the European Chapter of the Association for Computational Linguistics: Tutorials |
---|---|
Abbreviated title | EACL 2021 |
Country/Territory | Unknown |
Period | 19/04/21 → 23/04/21 |
Internet address |