Statistical Ranking in Tactical Generation

In this paper we describe and evaluate several 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 (and several variants) are trained and tested: an

• Type: Conference
• Year: 2006
• Where: EMNLP
• Authors: Erik Velldal, Stephan Oepen
• Keywords: EMNLP 2006, EMNLP 2007, Language Model, Maximum Entropy Model, Ò-gram Language Model