The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation

Tobias Domhan, Eva Hasler, Ke Tran, Sony Trenous, Bill Byrne, Felix Hieber


Abstract
Vocabulary selection, or lexical shortlisting, is a well-known technique to improve latency of Neural Machine Translation models by constraining the set of allowed output words during inference. The chosen set is typically determined by separately trained alignment model parameters, independent of the source-sentence context at inference time. While vocabulary selection appears competitive with respect to automatic quality metrics in prior work, we show that it can fail to select the right set of output words, particularly for semantically non-compositional linguistic phenomena such as idiomatic expressions, leading to reduced translation quality as perceived by humans. Trading off latency for quality by increasing the size of the allowed set is often not an option in real-world scenarios. We propose a model of vocabulary selection, integrated into the neural translation model, that predicts the set of allowed output words from contextualized encoder representations. This restores translation quality of an unconstrained system, as measured by human evaluations on WMT newstest2020 and idiomatic expressions, at an inference latency competitive with alignment-based selection using aggressive thresholds, thereby removing the dependency on separately trained alignment models.
Anthology ID:
2022.naacl-main.136
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1861–1874
Language:
URL:
https://aclanthology.org/2022.naacl-main.136
DOI:
10.18653/v1/2022.naacl-main.136
Bibkey:
Cite (ACL):
Tobias Domhan, Eva Hasler, Ke Tran, Sony Trenous, Bill Byrne, and Felix Hieber. 2022. The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1861–1874, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation (Domhan et al., NAACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2022.naacl-main.136.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2022.naacl-main.136.mp4
Code
 awslabs/sockeye