Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora
This work addresses the challenge of building translation resources without parallel data, which is incremental as it builds on latent-variable models by adding an agreement mechanism.
The paper tackles the problem of learning parallel lexicons and phrases from non-parallel corpora by introducing an agreement-based approach that encourages two asymmetric translation models to agree on alignments, resulting in significant improvements in alignment and translation performance on a Chinese-English dataset.
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.