Difference between revisions of "Vogal et al, COLING 1996"

From Cohen Courses
Jump to navigationJump to search
Line 16: Line 16:
  
 
== Previous work ==
 
== Previous work ==
IBM Model 1 defines the probability of a sentence <math>s_1^J</math> being translated to a sentence <math>t_1^I</math> using the alignment <math>a_1^J</math> as:
+
IBM Model 1 defines the probability of a sentence <math>s_1^J</math>, with length <math>J</math>, being translated to a sentence <math>t_1^I</math>, with length <math>I</math>, with the alignment <math>a_1^J</math> as:
  
 
<math>Pr(t,a|s) = \frac{\epsilon}{(J+1)^{I}}\prod_{j=1}^{J}{tr(t_j|s_{a(j)})}</math>
 
<math>Pr(t,a|s) = \frac{\epsilon}{(J+1)^{I}}\prod_{j=1}^{J}{tr(t_j|s_{a(j)})}</math>

Revision as of 13:46, 23 September 2011

Citation

Vogel, S., Ney, H., & Tillmann, C. (1996). Hmm-based word alignment in statistical translation. In Proceedings of the 16th conference on Computational linguistics - Volume 2, COLING ’96, pp. 836–841, Stroudsburg, PA, USA. Association for Computational Linguistics.

Online version

ACM

Summary

Word Alignments map the word correspondence between two parallel sentences in different languages.

This work extends IBM models 1 and 2, which models lexical translation probabilities and absolute distortion probabilities, by also modeling relative distortion.

The relative distortion is modeled by applying a first-order HMM, where each alignment probabilities are dependent on the distortion of the previous alignment.

Previous work

IBM Model 1 defines the probability of a sentence , with length , being translated to a sentence , with length , with the alignment as:


Algorithm

While IBM Model 2 attempts to model the absolute distortion of words in sentence pairs , alignments have a strong tendency to maintain the local neighborhood after translation.