Paper: Inner-Outer Bracket Models For Word Alignment Using Hidden Blocks

ACL ID H05-1023
Title Inner-Outer Bracket Models For Word Alignment Using Hidden Blocks
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005
Authors

Most statistical translation systems are based on phrase translation pairs, or “blocks”, which are obtained mainly from word alignment. We use blocks to infer better word alignment and improved word alignment which, in turn, leads to better inference of blocks. We propose two new probabilistic models based on the inner- outersegmentationsanduseEMalgorithms for estimating the models’ parameters. The first model recovers IBM Model-1 as a spe- cial case. Both models outperform bi- directional IBM Model-4 in terms of word alignment accuracy by 10% absolute on the F-measure. Using blocks obtained from the models in actual translation systems yields statistically significant improvements in Chinese-English SMT evaluation.