Adaptive Weighting for Neural Machine Translation

Yachao Li, Junhui Li, Min Zhang


Abstract
In the popular sequence to sequence (seq2seq) neural machine translation (NMT), there exist many weighted sum models (WSMs), each of which takes a set of input and generates one output. However, the weights in a WSM are independent of each other and fixed for all inputs, suggesting that by ignoring different needs of inputs, the WSM lacks effective control on the influence of each input. In this paper, we propose adaptive weighting for WSMs to control the contribution of each input. Specifically, we apply adaptive weighting for both GRU and the output state in NMT. Experimentation on Chinese-to-English translation and English-to-German translation demonstrates that the proposed adaptive weighting is able to much improve translation accuracy by achieving significant improvement of 1.49 and 0.92 BLEU points for the two translation tasks. Moreover, we discuss in-depth on what type of information is encoded in the encoder and how information influences the generation of target words in the decoder.
Anthology ID:
C18-1257
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3038–3048
Language:
URL:
https://aclanthology.org/C18-1257
DOI:
Bibkey:
Cite (ACL):
Yachao Li, Junhui Li, and Min Zhang. 2018. Adaptive Weighting for Neural Machine Translation. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3038–3048, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Adaptive Weighting for Neural Machine Translation (Li et al., COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/C18-1257.pdf
Code
 liyc7711/weighted-nmt