Maximum Entropy Models for Realization Ranking (2005)
by
Erik Velldal
,
Stephan Oepen
| Venue: | In Proceedings of the 10th Machine Translation Summit (pp. 109 |
| Citations: | 16 - 1 self |
BibTeX
@INPROCEEDINGS{Velldal05maximumentropy,
author = {Erik Velldal and Stephan Oepen},
title = {Maximum Entropy Models for Realization Ranking},
booktitle = {In Proceedings of the 10th Machine Translation Summit (pp. 109},
year = {2005},
pages = {116}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
In this paper we describe and evaluate di#erent statistical models for the task of realization ranking, i.e. the problem of discriminating between competing surface realizations generated for a given input semantics. Three models are trained and tested; an n-gram language model, a discriminative maximum entropy model using structural features, and a combination of these two. Our realization component forms part of a larger, hybrid MT system.
