Natural Language Inference via Dependency Tree Mapping: An Application to Question Answering

Punyakanok, Vasin; Roth, Dan; Yih, Wen-tau

Permalink

https://hdl.handle.net/2142/11100 Copy

Description

Title

Natural Language Inference via Dependency Tree Mapping: An Application to Question Answering

Author(s)

• Punyakanok, Vasin
• Roth, Dan
• Yih, Wen-tau

Issue Date

2004-01

Keyword(s)

Natural Language Processing

Abstract

We describe an approach for answer selection in a free form question answering task. In order to go beyond a key-word based matching in selecting answers to questions, one would like to develop a principled way for the answer selection process that incorporates both syntactic and semantic information. We achieve this goal by (1) representing both questions and candidate passages using dependency trees, augmented with semantic information such as named entities, and (2) computing a generalized edit distance between a candidate passage representation and the question representation, a distance which aims to capture some level of meaning similarity. The sentence that best answers a question is determined to be the one that minimizes the generalized edit distance we define, computed via a dynamic programming based approximate tree matching algorithm. We evaluate the approach on question-answer pairs taken from previous TREC Q/A competitions. Preliminary experiments show its potential by significantly outperforming common bag-of-word scoring methods.

Type of Resource

text

Permalink

http://hdl.handle.net/2142/11100

Copyright and License Information

You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the University of Illinois at Urbana-Champaign Computer Science Department under terms that include this permission. All other rights are reserved by the author(s).

Owning Collections