Factoid vs. non-factoid question identification: an ensemble learning approach

Alaa Mohasseb; Andreas Kanavos

doi:10.5220/0011525900003318

Factoid vs. non-factoid question identification: an ensemble learning approach

Alaa Mohasseb, Andreas Kanavos

Ionian University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

357 Downloads (Pure)

Abstract

Question Classification is one of the most important applications of information retrieval. Identifying the correct question type constitutes the main step to enhance the performance of question answering systems. However, distinguishing between factoid and non-factoid questions is considered a challenging problem. In this paper, a grammatical based framework has been adapted for question identification. Ensemble Learning models were used for the classification process in which experimental results show that the combination of question grammatical features along with the ensemble learning models helped in achieving a good level of accuracy.

Original language	English
Title of host publication	Proceedings of the 18th International Conference on Web Information Systems and Technologies (WEBIST)
Editors	Stefan Decker, Francisco Domínguez Mayo, Massimo Marchiori, Joaquim Filipe
Publisher	SciTePress
Pages	265-271
ISBN (Print)	9789897586132
DOIs	https://doi.org/10.5220/0011525900003318
Publication status	Published - 28 Oct 2022
Event	18th International Conference on Web Information Systems and Technologies - Valletta, Malta Duration: 25 Oct 2022 → 27 Oct 2022 https://webist.scitevents.org/

Publication series

Name	ScitePress WEBIST Proceedings Series
Publisher	ScitePress
ISSN (Print)	2184-3252

Conference

Conference	18th International Conference on Web Information Systems and Technologies
Abbreviated title	(WEBIST 2022)
Country/Territory	Malta
City	Valletta
Period	25/10/22 → 27/10/22
Internet address	https://webist.scitevents.org/

Keywords

Question Classification
Grammatical Features
Factoid Questions
Information Retrieval
Machine Learning
Ensemble Learning

Access to Document

10.5220/0011525900003318

Factoid vs. Non factoid Question IdentificationAccepted author manuscript (Post-print), 127 KB

Cite this

Mohasseb, A., & Kanavos, A. (2022). Factoid vs. non-factoid question identification: an ensemble learning approach. In S. Decker, F. D. Mayo, M. Marchiori, & J. Filipe (Eds.), Proceedings of the 18th International Conference on Web Information Systems and Technologies (WEBIST) (pp. 265-271). (ScitePress WEBIST Proceedings Series). SciTePress. https://doi.org/10.5220/0011525900003318

Mohasseb, Alaa ; Kanavos, Andreas. / Factoid vs. non-factoid question identification: an ensemble learning approach. Proceedings of the 18th International Conference on Web Information Systems and Technologies (WEBIST). editor / Stefan Decker ; Francisco Domínguez Mayo ; Massimo Marchiori ; Joaquim Filipe. SciTePress, 2022. pp. 265-271 (ScitePress WEBIST Proceedings Series).

@inproceedings{2638ca1f9f3f4101883fe4b2b760d433,

title = "Factoid vs. non-factoid question identification: an ensemble learning approach",

abstract = "Question Classification is one of the most important applications of information retrieval. Identifying the correct question type constitutes the main step to enhance the performance of question answering systems. However, distinguishing between factoid and non-factoid questions is considered a challenging problem. In this paper, a grammatical based framework has been adapted for question identification. Ensemble Learning models were used for the classification process in which experimental results show that the combination of question grammatical features along with the ensemble learning models helped in achieving a good level of accuracy.",

keywords = "Question Classification, Grammatical Features, Factoid Questions, Information Retrieval, Machine Learning, Ensemble Learning",

author = "Alaa Mohasseb and Andreas Kanavos",

year = "2022",

month = oct,

day = "28",

doi = "10.5220/0011525900003318",

language = "English",

isbn = "9789897586132",

series = "ScitePress WEBIST Proceedings Series",

publisher = "SciTePress",

pages = "265--271",

editor = "Decker, {Stefan } and Mayo, {Francisco Dom{\'i}nguez } and Massimo Marchiori and Joaquim Filipe",

booktitle = "Proceedings of the 18th International Conference on Web Information Systems and Technologies (WEBIST)",

note = "18th International Conference on Web Information Systems and Technologies, (WEBIST 2022) ; Conference date: 25-10-2022 Through 27-10-2022",

url = "https://webist.scitevents.org/",

}

Mohasseb, A & Kanavos, A 2022, Factoid vs. non-factoid question identification: an ensemble learning approach. in S Decker, FD Mayo, M Marchiori & J Filipe (eds), Proceedings of the 18th International Conference on Web Information Systems and Technologies (WEBIST). ScitePress WEBIST Proceedings Series, SciTePress, pp. 265-271, 18th International Conference on Web Information Systems and Technologies, Valletta, Malta, 25/10/22. https://doi.org/10.5220/0011525900003318

Factoid vs. non-factoid question identification: an ensemble learning approach. / Mohasseb, Alaa; Kanavos, Andreas.
Proceedings of the 18th International Conference on Web Information Systems and Technologies (WEBIST). ed. / Stefan Decker; Francisco Domínguez Mayo; Massimo Marchiori; Joaquim Filipe. SciTePress, 2022. p. 265-271 (ScitePress WEBIST Proceedings Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Factoid vs. non-factoid question identification: an ensemble learning approach

AU - Mohasseb, Alaa

AU - Kanavos, Andreas

PY - 2022/10/28

Y1 - 2022/10/28

N2 - Question Classification is one of the most important applications of information retrieval. Identifying the correct question type constitutes the main step to enhance the performance of question answering systems. However, distinguishing between factoid and non-factoid questions is considered a challenging problem. In this paper, a grammatical based framework has been adapted for question identification. Ensemble Learning models were used for the classification process in which experimental results show that the combination of question grammatical features along with the ensemble learning models helped in achieving a good level of accuracy.

AB - Question Classification is one of the most important applications of information retrieval. Identifying the correct question type constitutes the main step to enhance the performance of question answering systems. However, distinguishing between factoid and non-factoid questions is considered a challenging problem. In this paper, a grammatical based framework has been adapted for question identification. Ensemble Learning models were used for the classification process in which experimental results show that the combination of question grammatical features along with the ensemble learning models helped in achieving a good level of accuracy.

KW - Question Classification

KW - Grammatical Features

KW - Factoid Questions

KW - Information Retrieval

KW - Machine Learning

KW - Ensemble Learning

UR - https://webist.scitevents.org/ImportantDates.aspx

U2 - 10.5220/0011525900003318

DO - 10.5220/0011525900003318

M3 - Conference contribution

SN - 9789897586132

T3 - ScitePress WEBIST Proceedings Series

SP - 265

EP - 271

BT - Proceedings of the 18th International Conference on Web Information Systems and Technologies (WEBIST)

A2 - Decker, Stefan

A2 - Mayo, Francisco Domínguez

A2 - Marchiori, Massimo

A2 - Filipe, Joaquim

PB - SciTePress

T2 - 18th International Conference on Web Information Systems and Technologies

Y2 - 25 October 2022 through 27 October 2022

ER -

Factoid vs. non-factoid question identification: an ensemble learning approach

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this