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

TY - GEN

T1 - A strong baseline for learning cross-lingualword embeddings from sentence alignments

AU - Levy, Omer

AU - Søgaard, Anders

AU - Goldberg, Yoav

PY - 2017

Y1 - 2017

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85021664953&partnerID=8YFLogxK

M3 - Article in proceedings

AN - SCOPUS:85021664953

VL - 1

SP - 765

EP - 774

BT - Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics

T2 - 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017

Y2 - 3 April 2017 through 7 April 2017

ER -