Answering complex questions using query-focused summarization technique

Yllias Chali, Shafiq Rayhan Joty

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

2 Citations (Scopus)

Abstract

Unlike simple questions, complex questions cannot he answered by simply extracting named entities. These questions require inferencing and synthesizing information from multiple documents that can be seen as a kind of topic-oriented, informative multi-document summarization. In this paper, we have experimented with one empirical and two unsupervised statistical machine learning techniques: k-means and Expectation Maximization (EM), for computing relative importance of the sentences. The feature set includes different kinds of features: lexical, lexical semantic, cosine similarity, basic element, tree kernel based syntactic and shallow-semantic. A gradient descent local search technique is used to learn the optimal weights of the features. The effects of the different features are also shown for all the methods of generating summaries.

Original languageEnglish
Title of host publicationProceedings - International Conference on Tools with Artificial Intelligence, ICTAI
Pages131-134
Number of pages4
Volume2
DOIs
Publication statusPublished - 22 Dec 2008
Externally publishedYes
Event20th IEEE International Conference on Tools with Artificial Intelligence, ICTAI'08 - Dayton, OH, United States
Duration: 3 Nov 20085 Nov 2008

Other

Other20th IEEE International Conference on Tools with Artificial Intelligence, ICTAI'08
CountryUnited States
CityDayton, OH
Period3/11/085/11/08

Fingerprint

Semantics
Syntactics
Learning systems

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Science Applications

Cite this

Chali, Y., & Rayhan Joty, S. (2008). Answering complex questions using query-focused summarization technique. In Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI (Vol. 2, pp. 131-134). [4669765] https://doi.org/10.1109/ICTAI.2008.84

Answering complex questions using query-focused summarization technique. / Chali, Yllias; Rayhan Joty, Shafiq.

Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI. Vol. 2 2008. p. 131-134 4669765.

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

Chali, Y & Rayhan Joty, S 2008, Answering complex questions using query-focused summarization technique. in Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI. vol. 2, 4669765, pp. 131-134, 20th IEEE International Conference on Tools with Artificial Intelligence, ICTAI'08, Dayton, OH, United States, 3/11/08. https://doi.org/10.1109/ICTAI.2008.84
Chali Y, Rayhan Joty S. Answering complex questions using query-focused summarization technique. In Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI. Vol. 2. 2008. p. 131-134. 4669765 https://doi.org/10.1109/ICTAI.2008.84
Chali, Yllias ; Rayhan Joty, Shafiq. / Answering complex questions using query-focused summarization technique. Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI. Vol. 2 2008. pp. 131-134
@inproceedings{5ded95bc6f224e2aa90251d2e81abf13,
title = "Answering complex questions using query-focused summarization technique",
abstract = "Unlike simple questions, complex questions cannot he answered by simply extracting named entities. These questions require inferencing and synthesizing information from multiple documents that can be seen as a kind of topic-oriented, informative multi-document summarization. In this paper, we have experimented with one empirical and two unsupervised statistical machine learning techniques: k-means and Expectation Maximization (EM), for computing relative importance of the sentences. The feature set includes different kinds of features: lexical, lexical semantic, cosine similarity, basic element, tree kernel based syntactic and shallow-semantic. A gradient descent local search technique is used to learn the optimal weights of the features. The effects of the different features are also shown for all the methods of generating summaries.",
author = "Yllias Chali and {Rayhan Joty}, Shafiq",
year = "2008",
month = "12",
day = "22",
doi = "10.1109/ICTAI.2008.84",
language = "English",
isbn = "9780769534404",
volume = "2",
pages = "131--134",
booktitle = "Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI",

}

TY - GEN

T1 - Answering complex questions using query-focused summarization technique

AU - Chali, Yllias

AU - Rayhan Joty, Shafiq

PY - 2008/12/22

Y1 - 2008/12/22

N2 - Unlike simple questions, complex questions cannot he answered by simply extracting named entities. These questions require inferencing and synthesizing information from multiple documents that can be seen as a kind of topic-oriented, informative multi-document summarization. In this paper, we have experimented with one empirical and two unsupervised statistical machine learning techniques: k-means and Expectation Maximization (EM), for computing relative importance of the sentences. The feature set includes different kinds of features: lexical, lexical semantic, cosine similarity, basic element, tree kernel based syntactic and shallow-semantic. A gradient descent local search technique is used to learn the optimal weights of the features. The effects of the different features are also shown for all the methods of generating summaries.

AB - Unlike simple questions, complex questions cannot he answered by simply extracting named entities. These questions require inferencing and synthesizing information from multiple documents that can be seen as a kind of topic-oriented, informative multi-document summarization. In this paper, we have experimented with one empirical and two unsupervised statistical machine learning techniques: k-means and Expectation Maximization (EM), for computing relative importance of the sentences. The feature set includes different kinds of features: lexical, lexical semantic, cosine similarity, basic element, tree kernel based syntactic and shallow-semantic. A gradient descent local search technique is used to learn the optimal weights of the features. The effects of the different features are also shown for all the methods of generating summaries.

UR - http://www.scopus.com/inward/record.url?scp=57649156232&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57649156232&partnerID=8YFLogxK

U2 - 10.1109/ICTAI.2008.84

DO - 10.1109/ICTAI.2008.84

M3 - Conference contribution

SN - 9780769534404

VL - 2

SP - 131

EP - 134

BT - Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI

ER -