Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search

Chris Hokamp, Qun Liu


Abstract
We present Grid Beam Search (GBS), an algorithm which extends beam search to allow the inclusion of pre-specified lexical constraints. The algorithm can be used with any model which generates sequences token by token. Lexical constraints take the form of phrases or words that must be present in the output sequence. This is a very general way to incorporate auxillary knowledge into a model’s output without requiring any modification of the parameters or training data. We demonstrate the feasibility and flexibility of Lexically Constrained Decoding by conducting experiments on Neural Interactive-Predictive Translation, as well as Domain Adaptation for Neural Machine Translation. Experiments show that GBS can provide large improvements in translation quality in interactive scenarios, and that, even without any user input, GBS can be used to achieve significant gains in performance in domain adaptation scenarios.
Anthology ID:
P17-1141
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1535–1546
Language:
URL:
https://aclanthology.org/P17-1141
DOI:
10.18653/v1/P17-1141
Bibkey:
Cite (ACL):
Chris Hokamp and Qun Liu. 2017. Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1535–1546, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search (Hokamp & Liu, ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1141.pdf
Code
 chrishokamp/constrained_decoding