Recurrent Positional Embedding for Neural Machine Translation

Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita


Abstract
In the Transformer network architecture, positional embeddings are used to encode order dependencies into the input representation. However, this input representation only involves static order dependencies based on discrete numerical information, that is, are independent of word content. To address this issue, this work proposes a recurrent positional embedding approach based on word vector. In this approach, these recurrent positional embeddings are learned by a recurrent neural network, encoding word content-based order dependencies into the input representation. They are then integrated into the existing multi-head self-attention model as independent heads or part of each head. The experimental results revealed that the proposed approach improved translation performance over that of the state-of-the-art Transformer baseline in WMT’14 English-to-German and NIST Chinese-to-English translation tasks.
Anthology ID:
D19-1139
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:
1361–1367
Language:
URL:
https://aclanthology.org/D19-1139
DOI:
10.18653/v1/D19-1139
Bibkey:
Cite (ACL):
Kehai Chen, Rui Wang, Masao Utiyama, and Eiichiro Sumita. 2019. Recurrent Positional Embedding for 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 1361–1367, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Recurrent Positional Embedding for Neural Machine Translation (Chen et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1139.pdf