A Discriminative Latent-Variable Model for Bilingual Lexicon Induction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ruder, Sebastian, Cotterell, Ryan, Kementchedjhieva, Yova, Søgaard, Anders
Format: Preprint
Published: 2018
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911791821357056
author Ruder, Sebastian
Cotterell, Ryan
Kementchedjhieva, Yova
Søgaard, Anders
author_facet Ruder, Sebastian
Cotterell, Ryan
Kementchedjhieva, Yova
Søgaard, Anders
contents We introduce a novel discriminative latent variable model for bilingual lexicon induction. Our model combines the bipartite matching dictionary prior of Haghighi et al. (2008) with a representation-based approach (Artetxe et al., 2017). To train the model, we derive an efficient Viterbi EM algorithm. We provide empirical results on six language pairs under two metrics and show that the prior improves the induced bilingual lexicons. We also demonstrate how previous work may be viewed as a similarly fashioned latent-variable model, albeit with a different prior.
format Preprint
id arxiv_https___arxiv_org_abs_1808_09334
institution arXiv
publishDate 2018
record_format arxiv
spellingShingle A Discriminative Latent-Variable Model for Bilingual Lexicon Induction
Ruder, Sebastian
Cotterell, Ryan
Kementchedjhieva, Yova
Søgaard, Anders
Computation and Language
Machine Learning
We introduce a novel discriminative latent variable model for bilingual lexicon induction. Our model combines the bipartite matching dictionary prior of Haghighi et al. (2008) with a representation-based approach (Artetxe et al., 2017). To train the model, we derive an efficient Viterbi EM algorithm. We provide empirical results on six language pairs under two metrics and show that the prior improves the induced bilingual lexicons. We also demonstrate how previous work may be viewed as a similarly fashioned latent-variable model, albeit with a different prior.
title A Discriminative Latent-Variable Model for Bilingual Lexicon Induction
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/1808.09334