Improving graph-based random walks for complex question answering using syntactic, shallow semantic and extended string subsequence kernels

Yllias Chali, Sadid A. Hasan, Shafiq Rayhan Joty

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

The task of answering complex questions requires inferencing and synthesizing information from multiple documents that can be seen as a kind of topic-oriented, informative multi-document summarization. In generic summarization the stochastic, graph-based random walk method to compute the relative importance of textual units (i.e. sentences) is proved to be very successful. However, the major limitation of the TFIDF approach is that it only retains the frequency of the words and does not take into account the sequence, syntactic and semantic information. This paper presents the impact of syntactic and semantic information in the graph-based random walk method for answering complex questions. Initially, we apply tree kernel functions to perform the similarity measures between sentences in the random walk framework. Then, we extend our work further to incorporate the Extended String Subsequence Kernel (ESSK) to perform the task in a similar manner. Experimental results show the effectiveness of the use of kernels to include the syntactic and semantic information for this task.

Original languageEnglish
Pages (from-to)843-855
Number of pages13
JournalInformation Processing and Management
Volume47
Issue number6
DOIs
Publication statusPublished - 1 Nov 2011
Externally publishedYes

Fingerprint

Syntactics
Semantics
semantics
Kernel
Random walk
Question answering
Graph
Summarization

Keywords

  • Complex question answering
  • Extended string subsequence kernel
  • Graph-based method
  • Shallow semantic kernel
  • Syntactic kernel

ASJC Scopus subject areas

  • Media Technology
  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences
  • Management Science and Operations Research

Cite this

Improving graph-based random walks for complex question answering using syntactic, shallow semantic and extended string subsequence kernels. / Chali, Yllias; Hasan, Sadid A.; Rayhan Joty, Shafiq.

In: Information Processing and Management, Vol. 47, No. 6, 01.11.2011, p. 843-855.

Research output: Contribution to journalArticle

@article{7806c84fc0814e8aa93740eaf28b8912,
title = "Improving graph-based random walks for complex question answering using syntactic, shallow semantic and extended string subsequence kernels",
abstract = "The task of answering complex questions requires inferencing and synthesizing information from multiple documents that can be seen as a kind of topic-oriented, informative multi-document summarization. In generic summarization the stochastic, graph-based random walk method to compute the relative importance of textual units (i.e. sentences) is proved to be very successful. However, the major limitation of the TFIDF approach is that it only retains the frequency of the words and does not take into account the sequence, syntactic and semantic information. This paper presents the impact of syntactic and semantic information in the graph-based random walk method for answering complex questions. Initially, we apply tree kernel functions to perform the similarity measures between sentences in the random walk framework. Then, we extend our work further to incorporate the Extended String Subsequence Kernel (ESSK) to perform the task in a similar manner. Experimental results show the effectiveness of the use of kernels to include the syntactic and semantic information for this task.",
keywords = "Complex question answering, Extended string subsequence kernel, Graph-based method, Shallow semantic kernel, Syntactic kernel",
author = "Yllias Chali and Hasan, {Sadid A.} and {Rayhan Joty}, Shafiq",
year = "2011",
month = "11",
day = "1",
doi = "10.1016/j.ipm.2010.10.002",
language = "English",
volume = "47",
pages = "843--855",
journal = "Information Processing and Management",
issn = "0306-4573",
publisher = "Elsevier Limited",
number = "6",

}

TY - JOUR

T1 - Improving graph-based random walks for complex question answering using syntactic, shallow semantic and extended string subsequence kernels

AU - Chali, Yllias

AU - Hasan, Sadid A.

AU - Rayhan Joty, Shafiq

PY - 2011/11/1

Y1 - 2011/11/1

N2 - The task of answering complex questions requires inferencing and synthesizing information from multiple documents that can be seen as a kind of topic-oriented, informative multi-document summarization. In generic summarization the stochastic, graph-based random walk method to compute the relative importance of textual units (i.e. sentences) is proved to be very successful. However, the major limitation of the TFIDF approach is that it only retains the frequency of the words and does not take into account the sequence, syntactic and semantic information. This paper presents the impact of syntactic and semantic information in the graph-based random walk method for answering complex questions. Initially, we apply tree kernel functions to perform the similarity measures between sentences in the random walk framework. Then, we extend our work further to incorporate the Extended String Subsequence Kernel (ESSK) to perform the task in a similar manner. Experimental results show the effectiveness of the use of kernels to include the syntactic and semantic information for this task.

AB - The task of answering complex questions requires inferencing and synthesizing information from multiple documents that can be seen as a kind of topic-oriented, informative multi-document summarization. In generic summarization the stochastic, graph-based random walk method to compute the relative importance of textual units (i.e. sentences) is proved to be very successful. However, the major limitation of the TFIDF approach is that it only retains the frequency of the words and does not take into account the sequence, syntactic and semantic information. This paper presents the impact of syntactic and semantic information in the graph-based random walk method for answering complex questions. Initially, we apply tree kernel functions to perform the similarity measures between sentences in the random walk framework. Then, we extend our work further to incorporate the Extended String Subsequence Kernel (ESSK) to perform the task in a similar manner. Experimental results show the effectiveness of the use of kernels to include the syntactic and semantic information for this task.

KW - Complex question answering

KW - Extended string subsequence kernel

KW - Graph-based method

KW - Shallow semantic kernel

KW - Syntactic kernel

UR - http://www.scopus.com/inward/record.url?scp=80052262254&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052262254&partnerID=8YFLogxK

U2 - 10.1016/j.ipm.2010.10.002

DO - 10.1016/j.ipm.2010.10.002

M3 - Article

VL - 47

SP - 843

EP - 855

JO - Information Processing and Management

JF - Information Processing and Management

SN - 0306-4573

IS - 6

ER -