Identifying word translations from comparable corpora using latent topic models

摘要

A topic model outputs a set of multinomial distributions over words for each topic. In this paper, we investigate the value of bilingual topic models, i.e., a bilingual Latent Dirichlet Allocation model for finding translations of terms in comparable corpora without using any linguistic resources. Experiments on a document-aligned English-ItalianWikipedia corpus confirm that the developed methods which only use knowledge from word-topic distributions outperform methodsbased on similarity measures in the original word-document space. The best results, obtained by combining knowledge from word-topic distributions with similarity measures in the original space, are also reported.