Affordable Access

Neural Baselines for Word Alignments

Authors
  • Ngo-Ho, Ahn-Khoa
  • Yvon, François
Publication Date
Nov 02, 2019
Source
Kaleidoscope Open Archive
Keywords
Language
English
License
Unknown
External links

Abstract

Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems, or to perform quality estimation. In most areas of natural language processing, neural network models nowadays constitute the preferred approach, a situation that might also apply to word alignment models.In this work, we study and comprehensively evaluate neural models for unsupervised word alignment for four language pairs, contrasting several variants of neural models. We show that in most settings, neural versions of the IBM-1 and hidden Markov models vastly outperform their discrete counterparts. We also analyze typical alignment errors of the baselines that our models overcome to illustrate the benefits --- and the limitations --- of these new models for morphologically rich languages.

Report this publication

Statistics

Seen <100 times