Forskning ved Københavns Universitet - Københavns Universitet

Forside

A strong baseline for learning cross-lingualword embeddings from sentence alignments

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague. We observe that whether or not an algorithm uses a particular feature set (sentence IDs) accounts for a significant performance gap among these algorithms. This feature set is also used by traditional alignment algorithms, such as IBM Model-1, which demonstrate similar performance to stateof- The-art embedding algorithms on a variety of benchmarks. Overall, we observe that different algorithmic approaches for utilizing the sentence ID feature space result in similar performance. This paper draws both empirical and theoretical parallels between the embedding and alignment literature, and suggests that adding additional sources of information, which go beyond the traditional signal of bilingual sentence-aligned corpora, may substantially improve cross-lingual word embeddings, and that future baselines should at least take such features into account.

OriginalsprogEngelsk
TitelProceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics : Long papers
Antal sider10
Vol/bind1
ForlagAssociation for Computational Linguistics
Publikationsdato2017
Sider765-774
ISBN (Elektronisk)9781510838604
StatusUdgivet - 2017
Begivenhed15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spanien
Varighed: 3 apr. 20177 apr. 2017

Konference

Konference15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
LandSpanien
ByValencia
Periode03/04/201707/04/2017
SponsorCELI: Language Technology, eBay, et al., Grammarly, Textkernel, Thomson Reuters

ID: 214750842