Difference between revisions of "DeNero et al, EMNLP 2008"

From Cohen Courses
Jump to navigationJump to search
Line 11: Line 11:
 
Unlike word-to-phrase alignments, computing the alignment expectations for phrase-to-phrase alignments is generally intractable due to the exponential growth of possible combination of phrases and alignments. Because of this, previous attempts for building a joint phrase alignment model have been unsuccessful.
 
Unlike word-to-phrase alignments, computing the alignment expectations for phrase-to-phrase alignments is generally intractable due to the exponential growth of possible combination of phrases and alignments. Because of this, previous attempts for building a joint phrase alignment model have been unsuccessful.
  
This paper describes the first tractable Phrase-to-Phrase Alignment Model using Gibbs Sampling.
+
This paper describes the first tractable phrase-to-phrase Alignment Model, which relies on Gibbs Sampling to tackle the intractability problem.
  
 
Tests show translation improvements over Machine Translation Systems build using conventional methods.
 
Tests show translation improvements over Machine Translation Systems build using conventional methods.
  
 
== Algorithm ==
 
== Algorithm ==

Revision as of 14:38, 25 September 2011

Citation

Denero, J., Bouchard-ct, R., & Klein, D.(2008). Sampling alignment structure under a Bayesian translation model. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP '08). Association for Computational Linguistics, Stroudsburg, PA, USA, 314-323.

Online version

ACM

Summary

Unlike word-to-phrase alignments, computing the alignment expectations for phrase-to-phrase alignments is generally intractable due to the exponential growth of possible combination of phrases and alignments. Because of this, previous attempts for building a joint phrase alignment model have been unsuccessful.

This paper describes the first tractable phrase-to-phrase Alignment Model, which relies on Gibbs Sampling to tackle the intractability problem.

Tests show translation improvements over Machine Translation Systems build using conventional methods.

Algorithm