Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level Translation

Zhengxin Yang, Jinchao Zhang, Fandong Meng, Shuhao Gu, Yang Feng, Jie Zhou


Abstract
Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations. The widely used method for document-level translation usually compresses the context information into a representation via hierarchical attention networks. However, this method neither considers the relationship between context words nor distinguishes the roles of context words. To address this problem, we propose a query-guided capsule networks to cluster context information into different perspectives from which the target translation may concern. Experiment results show that our method can significantly outperform strong baselines on multiple data sets of different domains.
Anthology ID:
D19-1164
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:
1527–1537
Language:
URL:
https://aclanthology.org/D19-1164
DOI:
10.18653/v1/D19-1164
Bibkey:
Cite (ACL):
Zhengxin Yang, Jinchao Zhang, Fandong Meng, Shuhao Gu, Yang Feng, and Jie Zhou. 2019. Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level 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 1527–1537, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level Translation (Yang et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-bitext-workshop/D19-1164.pdf