Simultaneous paraphrasing and translation by fine-tuning Transformer models

Rakesh Chada


Abstract
This paper describes the third place submission to the shared task on simultaneous translation and paraphrasing for language education at the 4th workshop on Neural Generation and Translation (WNGT) for ACL 2020. The final system leverages pre-trained translation models and uses a Transformer architecture combined with an oversampling strategy to achieve a competitive performance. This system significantly outperforms the baseline on Hungarian (27% absolute improvement in Weighted Macro F1 score) and Portuguese (33% absolute improvement) languages.
Anthology ID:
2020.ngt-1.23
Volume:
Proceedings of the Fourth Workshop on Neural Generation and Translation
Month:
July
Year:
2020
Address:
Online
Editors:
Alexandra Birch, Andrew Finch, Hiroaki Hayashi, Kenneth Heafield, Marcin Junczys-Dowmunt, Ioannis Konstas, Xian Li, Graham Neubig, Yusuke Oda
Venue:
NGT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
198–203
Language:
URL:
https://aclanthology.org/2020.ngt-1.23
DOI:
10.18653/v1/2020.ngt-1.23
Bibkey:
Cite (ACL):
Rakesh Chada. 2020. Simultaneous paraphrasing and translation by fine-tuning Transformer models. In Proceedings of the Fourth Workshop on Neural Generation and Translation, pages 198–203, Online. Association for Computational Linguistics.
Cite (Informal):
Simultaneous paraphrasing and translation by fine-tuning Transformer models (Chada, NGT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2020.ngt-1.23.pdf
Video:
 http://slideslive.com/38929837