Learning Unsupervised Word Translations Without Adversaries

Tanmoy Mukherjee, Makoto Yamada, Timothy Hospedales


Abstract
Word translation, or bilingual dictionary induction, is an important capability that impacts many multilingual language processing tasks. Recent research has shown that word translation can be achieved in an unsupervised manner, without parallel seed dictionaries or aligned corpora. However, state of the art methods unsupervised bilingual dictionary induction are based on generative adversarial models, and as such suffer from their well known problems of instability and hyper-parameter sensitivity. We present a statistical dependency-based approach to bilingual dictionary induction that is unsupervised – no seed dictionary or parallel corpora required; and introduces no adversary – therefore being much easier to train. Our method performs comparably to adversarial alternatives and outperforms prior non-adversarial methods.
Anthology ID:
D18-1063
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
627–632
Language:
URL:
https://aclanthology.org/D18-1063
DOI:
10.18653/v1/D18-1063
Bibkey:
Cite (ACL):
Tanmoy Mukherjee, Makoto Yamada, and Timothy Hospedales. 2018. Learning Unsupervised Word Translations Without Adversaries. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 627–632, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Learning Unsupervised Word Translations Without Adversaries (Mukherjee et al., EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/D18-1063.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-2/D18-1063.mp4