pith. sign in

arxiv: 1606.04597 · v1 · pith:CWOJV4YHnew · submitted 2016-06-15 · 💻 cs.CL

Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora

classification 💻 cs.CL
keywords agreement-basedlearningcorporalexiconsmodelsnon-parallelparallelphrase
0
0 comments X
read the original abstract

We introduce an agreement-based approach to learning parallel lexicons and phrases from non-parallel corpora. The basic idea is to encourage two asymmetric latent-variable translation models (i.e., source-to-target and target-to-source) to agree on identifying latent phrase and word alignments. The agreement is defined at both word and phrase levels. We develop a Viterbi EM algorithm for jointly training the two unidirectional models efficiently. Experiments on the Chinese-English dataset show that agreement-based learning significantly improves both alignment and translation performance.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.