Controlling Text Complexity in Neural Machine Translation

Sweta Agrawal, Marine Carpuat


Abstract
This work introduces a machine translation task where the output is aimed at audiences of different levels of target language proficiency. We collect a high quality dataset of news articles available in English and Spanish, written for diverse grade levels and propose a method to align segments across comparable bilingual articles. The resulting dataset makes it possible to train multi-task sequence to sequence models that can translate and simplify text jointly. We show that these multi-task models outperform pipeline approaches that translate and simplify text independently.
Anthology ID:
D19-1166
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1549–1564
Language:
URL:
https://aclanthology.org/D19-1166
DOI:
10.18653/v1/D19-1166
Bibkey:
Cite (ACL):
Sweta Agrawal and Marine Carpuat. 2019. Controlling Text Complexity in Neural Machine Translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1549–1564, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Controlling Text Complexity in Neural Machine Translation (Agrawal & Carpuat, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1166.pdf
Attachment:
 D19-1166.Attachment.zip
Code
 sweta20/ComplexityControlledMT
Data
Newsela