Difference between revisions of "Bansal et al, ACL 2011"
From Cohen Courses
Jump to navigationJump to search| Line 13: | Line 13: | ||
This [[Category::paper | work]] defines a phrase-to-phrase alignment model for Statistical [[Machine Translation]]. A model based on [[usesMethod::Hidden Markov Model | HMMs]] is defined based on the work presented in [[Vogal et al, COLING 1996]], and extending it discontinuous phrases (gappy phrases). | This [[Category::paper | work]] defines a phrase-to-phrase alignment model for Statistical [[Machine Translation]]. A model based on [[usesMethod::Hidden Markov Model | HMMs]] is defined based on the work presented in [[Vogal et al, COLING 1996]], and extending it discontinuous phrases (gappy phrases). | ||
| + | |||
| + | The quality of the alignments is further improved by employing alignment agreement | ||
== Description of the Method == | == Description of the Method == | ||
Revision as of 16:56, 19 October 2011
Contents
Note
still incomplete...
Citation
M. Bansal, C. Quirk, and R. Moore. 2011. Gappy phrasal alignment by agreement. In Proceedings of ACL.
Online version
Summary
This work defines a phrase-to-phrase alignment model for Statistical Machine Translation. A model based on HMMs is defined based on the work presented in Vogal et al, COLING 1996, and extending it discontinuous phrases (gappy phrases).
The quality of the alignments is further improved by employing alignment agreement
Description of the Method
Experimental Results
Related Work
The work in Marcus and Wong, EMNLP 2002, describes a joint probability distribution, which is used and extended in this work.
