Generalizing Procrustes Analysis for Better Bilingual Dictionary Induction

Yova Radoslavova Kementchedjhieva, Sebastian Ruder, Ryan Cotterell, Anders Søgaard

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

Abstract

Most recent approaches to bilingual dictionaryinduction find a linear alignment between theword vector spaces of two languages. Weshow that projecting the two languages ontoa third, latent space, rather than directly ontoeach other, while equivalent in terms of expressivity,makes it easier to learn approximatealignments. Our modified approach also allowsfor supporting languages to be includedin the alignment process, to obtain an even betterperformance in low resource settings.
OriginalsprogEngelsk
TitelProceedings of the 22nd Conference on Computational Natural Language Learning (CoNLL 2018)
ForlagAssociation for Computational Linguistics
Publikationsdato2018
Sider211–220
StatusUdgivet - 2018
Begivenhed22nd Conference on Computational Natural Language Learning (CoNLL 2018) - Brussels, Belgien
Varighed: 31 okt. 20181 nov. 2018

Konference

Konference22nd Conference on Computational Natural Language Learning (CoNLL 2018)
Land/OmrådeBelgien
ByBrussels
Periode31/10/201801/11/2018

Citationsformater