Language classification from bilingual word embedding graphs
arXiv:1607.05014
Abstract
We study the role of the second language in bilingual word embeddings in monolingual semantic evaluation tasks. We find strongly and weakly positive correlations between down-stream task performance and second language similarity to the target language. Additionally, we show how bilingual word embeddings can be employed for the task of semantic language classification and that joint semantic spaces vary in meaningful ways across second languages. Our results support the hypothesis that semantic language similarity is influenced by both structural similarity as well as geography/contact.
To be published at Coling 2016
References in corpus (6)
- BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
- Polyglot: Distributed Word Representations for Multilingual NLP
- Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change
- Multilingual Models for Compositional Distributed Semantics
- Separated by an Un-common Language: Towards Judgment Language Informed Vector Space Modeling
- Freshman or Fresher? Quantifying the Geographic Variation of Internet Language