Difference between revisions of "Birch et al, StatMT 2006"
From Cohen Courses
Jump to navigationJump to search| Line 8: | Line 8: | ||
== Summary == | == Summary == | ||
| − | The model proposed in [[Marcus and Wong, EMNLP 2002]] | + | 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]] |
This work describes a phrase alignment model, that uses [[Hill Climbing]] to restrict the possible search space of possible phrase segmentations and alignments. | This work describes a phrase alignment model, that uses [[Hill Climbing]] to restrict the possible search space of possible phrase segmentations and alignments. | ||
Revision as of 16:04, 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
This work describes a phrase alignment model, that uses Hill Climbing to restrict the possible search space of possible phrase segmentations and alignments.
