Language classification from bilingual word embedding graphs
Computation and Language
2016-10-12 v2
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.
Cite
@article{arxiv.1607.05014,
title = {Language classification from bilingual word embedding graphs},
author = {Steffen Eger and Armin Hoenen and Alexander Mehler},
journal= {arXiv preprint arXiv:1607.05014},
year = {2016}
}
Comments
To be published at Coling 2016