Publications
Authors:
  • Vassilina Nikoulina , Marc Dymetman
Citation:
2nd Workshop on Syntax and Structure in Statistical Translation (SSST-2), ACL 2008, Colombus, Ohio, USA, June 19, 2008
<BR> Full paper available on <a href=http://aclweb.org/anthology-new/W/W08/W08-0407.pdf > ACL Website </a>
Abstract:
We describe experiments on discriminating English to French phrase-based translations through the use of syntactic “coupling” features. Using a robust rule-based dependency parser, we parse both the English source and the French translation candidates from the nbest list returned by our phrase-based system;
we compute for each candidate a number of coupling features, that is, values that depend on the amount of alignment between edges in the source and target structures, and discriminatively train the weights of these coupling features. We compare different feature combinations. Although the improvements in terms
of automatic measures such as Bleu and Nist are inconclusive, an initial human assessment of the results appears to show certain qualitative
improvements.
Year:
2008
Report number:
2008/014
Attachments: