Difference between revisions of "Birch et al, StatMT 2006"
From Cohen Courses
Jump to navigationJump to search| Line 10: | Line 10: | ||
The model proposed in [[Marcus and Wong, EMNLP 2002]] provides a strong framework for phrase-to-phrase alignments, but its applicability is hamstrung by the computational complexity of the running [[UsesMethod:: Expectation Maximization | EM]] in the large space of latent variables generated from all possible phrases and alignments. | The model proposed in [[Marcus and Wong, EMNLP 2002]] provides a strong framework for phrase-to-phrase alignments, but its applicability is hamstrung by the computational complexity of the running [[UsesMethod:: Expectation Maximization | EM]] in the large space of latent variables generated from all possible phrases and alignments. | ||
| − | This work describes a phrase-to-phrase alignment model, uses word-to-phrase alignments to constrain the space of phrasal alignments, improving the scalability of the model and also the performance in the | + | This work describes a phrase-to-phrase alignment model, uses word-to-phrase alignments to constrain the space of phrasal alignments, improving the scalability of the model and also the performance in the [[AddressesProblem::Machine Translation]] task. |
Revision as of 16:09, 26 November 2011
Citation
Alexandra Birch, Chris Callison-Burch, and Miles Osborne. 2006. Constraining the phrase-based, joint probability statistical translation model. In The Conference for the Association for Machine Translation in the Americas.
Online version
Summary
The model proposed in Marcus and Wong, EMNLP 2002 provides a strong framework for phrase-to-phrase alignments, but its applicability is hamstrung by the computational complexity of the running EM in the large space of latent variables generated from all possible phrases and alignments.
This work describes a phrase-to-phrase alignment model, uses word-to-phrase alignments to constrain the space of phrasal alignments, improving the scalability of the model and also the performance in the Machine Translation task.
