PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Enriched syntax-based meaning representation for answer extraction
Grzegorz Chrupala and Georgiana Dinu
In: SIGIR 2010 Workshop: Query Representation and Understanding(2010).

Abstract

In Question Answering a major challenge is the fact that similar meaning is very often expressed with different surface realizations in questions and in sentences containing the answer. In this paper we propose an enriched syntax-based representation which helps deal with this widespread variability and provides a degree of generalization. We encode uncertainty about the syntactic structure of the question by using multiple alternative dependency parse trees. We then augment the question meaning representation by including multiple paraphrases of each dependency path, derived from distributional analysis of a large corpus.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
Information Retrieval & Textual Information Access
ID Code:8854
Deposited By:Grzegorz Chrupala
Deposited On:21 February 2012