Integrating weakly supervised word sense disambiguation into neural machine translation

Pu, Xiao (Nuance Communications) ; Henderson, James (Idiap Research Institute) ; Pappas, Nikolaos (Idiap Research Institute) ; Popescu-Belis, Andrei (School of Management and Engineering Vaud, HES-SO // University of Applied Sciences Western Switzerland)

This paper demonstrates that word sense disambiguation (WSD) can improve neural machine translation (NMT) by widening the source context considered when modeling the senses of potentially ambiguous words. We first introduce three adaptive clustering algorithms for WSD, based on k-means, Chinese restaurant processes, and random walks, which are then applied to large word contexts represented in a low-rank space and evaluated on SemEval shared-task data. We then learn word vectors jointly with sense vectors defined by our best WSD method, within a state-of-the-art NMT system. We show that the concatenation of these vectors, and the use of a sense selection mechanism based on the weighted average of sense vectors, outperforms several baselines including sense-aware ones. This is demonstrated by translation on five language pairs. The improvements are more than 1 BLEU point over strong NMT baselines, +4% accuracy over all ambiguous nouns and verbs, or +20% when scored manually over several challenging words.


Article Type:
scientifique
Faculty:
Ingénierie et Architecture
School:
HEIG-VD
Institute:
IICT - Institut des Technologies de l'Information et de la Communication
Subject(s):
Ingénierie
Date:
2018-12
Pagination:
15 p.
Published in:
Transactions of the Association for Computational Linguistics
Numeration (vol. no.):
2018, vol. 6, pp. 635-649
DOI:
ISSN:
2307-387X
Appears in Collection:



 Record created 2019-04-02, last modified 2019-04-30

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)