Observing the Learning Curve of NMT Systems With Regard to Linguistic Phenomena

Patrick Stadler, Vivien Macketanz, Eleftherios Avramidis


Abstract
In this paper we present our observations and evaluations by observing the linguistic performance of the system on several steps on the training process of various English-to-German Neural Machine Translation models. The linguistic performance is measured through a semi-automatic process using a test suite. Among several linguistic observations, we find that the translation quality of some linguistic categories decreased within the recorded iterations. Additionally, we notice some drops of the translation quality of certain categories when using a larger corpus.
Anthology ID:
2021.acl-srw.20
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop
Month:
August
Year:
2021
Address:
Online
Editors:
Jad Kabbara, Haitao Lin, Amandalynne Paullada, Jannis Vamvas
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
186–196
Language:
URL:
https://aclanthology.org/2021.acl-srw.20
DOI:
10.18653/v1/2021.acl-srw.20
Bibkey:
Cite (ACL):
Patrick Stadler, Vivien Macketanz, and Eleftherios Avramidis. 2021. Observing the Learning Curve of NMT Systems With Regard to Linguistic Phenomena. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 186–196, Online. Association for Computational Linguistics.
Cite (Informal):
Observing the Learning Curve of NMT Systems With Regard to Linguistic Phenomena (Stadler et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-srw.20.pdf
Video:
 https://aclanthology.org/2021.acl-srw.20.mp4