Common Contracts
3 similar Research Paper contracts
Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel CorporaResearch Paper • February 1st, 2017
We introduce an agreement-based ap- proach to learning parallel lexicons and phrases from non-parallel corpora. The basic idea is to encourage two asym- metric 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 de- fined at both word and phrase levels. We develop a Viterbi EM algorithm for jointly training the two unidirectional models ef- ficiently. Experiments on the Chinese- English dataset show that agreement- based learning significantly improves both alignment and translation performance.
Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel CorporaResearch Paper • June 6th, 2016
We introduce an agreement-based ap- proach to learning parallel lexicons and phrases from non-parallel corpora. The basic idea is to encourage two asym- metric 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 de- fined at both word and phrase levels. We develop a Viterbi EM algorithm for jointly training the two unidirectional models ef- ficiently. Experiments on the Chinese- English dataset show that agreement- based learning significantly improves both alignment and translation performance.
Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel CorporaResearch Paper • March 19th, 2016
We introduce an agreement-based ap- proach to learning parallel lexicons and phrases from non-parallel corpora. The basic idea is to encourage two asymmet- ric latent-variable translation models (i.e., source-to-target and target-to-source) to a- gree 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 efficient- ly. Experiments on the Chinese-English dataset show that agreement-based learn- ing significantly improves both alignment and translation performance.
