Using AnsProlog with Link Grammar and WordNet for QA with deep reasoning

Chitta Baral, Luis Tari

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

3 Citations (Scopus)

Abstract

Early question-answering (QA) approaches could only adequately answer fact-related questions and are insufficient in answering complex questions. More sophisticated QA systems utilize the semantics of words to answer complex questions. However, to answer certain kinds of complex questions, it is necessary to perform deep reasoning by utilizing the semantics of words as well as domain knowledge such as the effects and executability of actions. We propose a QA system that uses AnsProlog to represent domain knowledge and reason from the knowledge extracted by using Link Grammar and WordNet. We use the travel domain to illustrate our approach.

Original languageEnglish (US)
Title of host publicationProceedings - 9th International Conference on Information Technology, ICIT 2006
Pages125-128
Number of pages4
DOIs
StatePublished - 2007
Event9th International Conference on Information Technology, ICIT 2006 - Bhubaneswar, India
Duration: Dec 18 2006Dec 21 2006

Other

Other9th International Conference on Information Technology, ICIT 2006
CountryIndia
CityBhubaneswar
Period12/18/0612/21/06

Fingerprint

Semantics

ASJC Scopus subject areas

  • Information Systems
  • Software

Cite this

Baral, C., & Tari, L. (2007). Using AnsProlog with Link Grammar and WordNet for QA with deep reasoning. In Proceedings - 9th International Conference on Information Technology, ICIT 2006 (pp. 125-128). [4273169] https://doi.org/10.1109/ICIT.2006.90

Using AnsProlog with Link Grammar and WordNet for QA with deep reasoning. / Baral, Chitta; Tari, Luis.

Proceedings - 9th International Conference on Information Technology, ICIT 2006. 2007. p. 125-128 4273169.

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

Baral, C & Tari, L 2007, Using AnsProlog with Link Grammar and WordNet for QA with deep reasoning. in Proceedings - 9th International Conference on Information Technology, ICIT 2006., 4273169, pp. 125-128, 9th International Conference on Information Technology, ICIT 2006, Bhubaneswar, India, 12/18/06. https://doi.org/10.1109/ICIT.2006.90
Baral C, Tari L. Using AnsProlog with Link Grammar and WordNet for QA with deep reasoning. In Proceedings - 9th International Conference on Information Technology, ICIT 2006. 2007. p. 125-128. 4273169 https://doi.org/10.1109/ICIT.2006.90
Baral, Chitta ; Tari, Luis. / Using AnsProlog with Link Grammar and WordNet for QA with deep reasoning. Proceedings - 9th International Conference on Information Technology, ICIT 2006. 2007. pp. 125-128
@inproceedings{746afe09b5734095b2f9f7fb36804b32,
title = "Using AnsProlog with Link Grammar and WordNet for QA with deep reasoning",
abstract = "Early question-answering (QA) approaches could only adequately answer fact-related questions and are insufficient in answering complex questions. More sophisticated QA systems utilize the semantics of words to answer complex questions. However, to answer certain kinds of complex questions, it is necessary to perform deep reasoning by utilizing the semantics of words as well as domain knowledge such as the effects and executability of actions. We propose a QA system that uses AnsProlog to represent domain knowledge and reason from the knowledge extracted by using Link Grammar and WordNet. We use the travel domain to illustrate our approach.",
author = "Chitta Baral and Luis Tari",
year = "2007",
doi = "10.1109/ICIT.2006.90",
language = "English (US)",
isbn = "0769526357",
pages = "125--128",
booktitle = "Proceedings - 9th International Conference on Information Technology, ICIT 2006",

}

TY - GEN

T1 - Using AnsProlog with Link Grammar and WordNet for QA with deep reasoning

AU - Baral, Chitta

AU - Tari, Luis

PY - 2007

Y1 - 2007

N2 - Early question-answering (QA) approaches could only adequately answer fact-related questions and are insufficient in answering complex questions. More sophisticated QA systems utilize the semantics of words to answer complex questions. However, to answer certain kinds of complex questions, it is necessary to perform deep reasoning by utilizing the semantics of words as well as domain knowledge such as the effects and executability of actions. We propose a QA system that uses AnsProlog to represent domain knowledge and reason from the knowledge extracted by using Link Grammar and WordNet. We use the travel domain to illustrate our approach.

AB - Early question-answering (QA) approaches could only adequately answer fact-related questions and are insufficient in answering complex questions. More sophisticated QA systems utilize the semantics of words to answer complex questions. However, to answer certain kinds of complex questions, it is necessary to perform deep reasoning by utilizing the semantics of words as well as domain knowledge such as the effects and executability of actions. We propose a QA system that uses AnsProlog to represent domain knowledge and reason from the knowledge extracted by using Link Grammar and WordNet. We use the travel domain to illustrate our approach.

UR - http://www.scopus.com/inward/record.url?scp=36048997225&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36048997225&partnerID=8YFLogxK

U2 - 10.1109/ICIT.2006.90

DO - 10.1109/ICIT.2006.90

M3 - Conference contribution

AN - SCOPUS:36048997225

SN - 0769526357

SN - 9780769526355

SP - 125

EP - 128

BT - Proceedings - 9th International Conference on Information Technology, ICIT 2006

ER -