Answer Type Identificationfor Question Answering: Supervised Learning of Dependency Graph Patterns from Natural Language Questions

Andrew D. Walker, Panos Alexopoulos, Andrew Starkey, Jeff Z. Pan, Jose Manuel Gomez-Perez, Advaith Siddharthan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Question Answering research has long recognised that the identification of the type of answer being requested is a fundamental step in the interpretation of a question as a whole. Previous strategies have ranged from trivial keyword matches, to statistical analyses, to well-defined algorithms based on shallow syntactic parses with user-interaction for ambiguity resolution. A novel strategy combining deep NLP on both syntactic and dependency parses with supervised learning is introduced and results that improve on extant alternatives reported. The impact of the strategy on QALD is also evaluated with a proprietary Question Answering system and its positive results analysed.
Original languageEnglish
Title of host publicationSemantic Technology
Subtitle of host publication5th Joint International Conference, JIST 2015, Yichang, China, November 11-13, 2015, Revised Selected Papers
EditorsGuilin Qi, Kouji Kozaki, Jeff Z. Pan, Siwei Yu
Place of PublicationCham
PublisherSpringer International Publishing
Pages235-251
Number of pages17
ISBN (Electronic)978-3-319-31676-5
ISBN (Print)978-3-319-31675-8
DOIs
Publication statusPublished - 20 Mar 2016
Event5th Joint International Semantic Technology Conference - Yichang, China
Duration: 11 Nov 201513 Nov 2015
http://www.jist2015.org/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer, Cham
Volume9544
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference5th Joint International Semantic Technology Conference
Abbreviated titleJIST 2015
Country/TerritoryChina
CityYichang
Period11/11/1513/11/15
Internet address

Fingerprint

Dive into the research topics of 'Answer Type Identificationfor Question Answering: Supervised Learning of Dependency Graph Patterns from Natural Language Questions'. Together they form a unique fingerprint.

Cite this