Maximum Entropy Models for Realization Ranking

Erik Velldal, Stephan Oepen


Abstract
In this paper we describe and evaluate different 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.
Anthology ID:
2005.mtsummit-papers.15
Volume:
Proceedings of Machine Translation Summit X: Papers
Month:
September 13-15
Year:
2005
Address:
Phuket, Thailand
Venue:
MTSummit
SIG:
Publisher:
Note:
Pages:
109–116
Language:
URL:
https://aclanthology.org/2005.mtsummit-papers.15
DOI:
Bibkey:
Cite (ACL):
Erik Velldal and Stephan Oepen. 2005. Maximum Entropy Models for Realization Ranking. In Proceedings of Machine Translation Summit X: Papers, pages 109–116, Phuket, Thailand.
Cite (Informal):
Maximum Entropy Models for Realization Ranking (Velldal & Oepen, MTSummit 2005)
Copy Citation:
PDF:
https://aclanthology.org/2005.mtsummit-papers.15.pdf