Question classification using support vector machine and pattern matching

Ali Muttaleb Hasan, Lailatul Qadri Zakaria

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Question classification plays a crucial role in the question answering system, and it aim to accurately assign one or more labels to question based on expected answer type. Nonetheless, classifying user’s question is a very challenging task due to the flexibility of Natural Language where a question can be written in many different forms and information within the sentence may not be enough to effectively to classify the question. Limited researches have focused on question classification for Arabic question answering. In this research we used support vector machine (SVM) and pattern matching to classify question into three main classes which are “Who”, “Where” and “What”. The SVM leverage features such as n-gram and WordNet. The WordNet is used to map words in questions to their synonyms that have the same meaning. Five pattern were introduced to analyze “What” question and label the questions with “definition”, “person”, “location” or “object”. The dataset set used in this research consist of 200 question about Hadith from Sahih Al Bukhari. The experimental result scored F-measure at 95.2%, 84.6%, and 83.6% respectively for “Who”, “Where” and “What”. The result show that the SVM classifier is useful to classify question in Arabic language.

Original languageEnglish
Pages (from-to)259-265
Number of pages7
JournalJournal of Theoretical and Applied Information Technology
Volume87
Issue number2
Publication statusPublished - 1 May 2016

Fingerprint

Pattern matching
Pattern Matching
Support vector machines
Support Vector Machine
WordNet
Classify
Labels
Question Answering System
N-gram
Question Answering
Leverage
Natural Language
Assign
Person
Classifiers
Flexibility
Classifier
Experimental Results

Keywords

  • Machine learning
  • Question classification system

ASJC Scopus subject areas

  • Computer Science(all)
  • Theoretical Computer Science

Cite this

Question classification using support vector machine and pattern matching. / Hasan, Ali Muttaleb; Zakaria, Lailatul Qadri.

In: Journal of Theoretical and Applied Information Technology, Vol. 87, No. 2, 01.05.2016, p. 259-265.

Research output: Contribution to journalArticle

@article{bcefa0656139426cad620decba288605,
title = "Question classification using support vector machine and pattern matching",
abstract = "Question classification plays a crucial role in the question answering system, and it aim to accurately assign one or more labels to question based on expected answer type. Nonetheless, classifying user’s question is a very challenging task due to the flexibility of Natural Language where a question can be written in many different forms and information within the sentence may not be enough to effectively to classify the question. Limited researches have focused on question classification for Arabic question answering. In this research we used support vector machine (SVM) and pattern matching to classify question into three main classes which are “Who”, “Where” and “What”. The SVM leverage features such as n-gram and WordNet. The WordNet is used to map words in questions to their synonyms that have the same meaning. Five pattern were introduced to analyze “What” question and label the questions with “definition”, “person”, “location” or “object”. The dataset set used in this research consist of 200 question about Hadith from Sahih Al Bukhari. The experimental result scored F-measure at 95.2{\%}, 84.6{\%}, and 83.6{\%} respectively for “Who”, “Where” and “What”. The result show that the SVM classifier is useful to classify question in Arabic language.",
keywords = "Machine learning, Question classification system",
author = "Hasan, {Ali Muttaleb} and Zakaria, {Lailatul Qadri}",
year = "2016",
month = "5",
day = "1",
language = "English",
volume = "87",
pages = "259--265",
journal = "Journal of Theoretical and Applied Information Technology",
issn = "1992-8645",
publisher = "Asian Research Publishing Network (ARPN)",
number = "2",

}

TY - JOUR

T1 - Question classification using support vector machine and pattern matching

AU - Hasan, Ali Muttaleb

AU - Zakaria, Lailatul Qadri

PY - 2016/5/1

Y1 - 2016/5/1

N2 - Question classification plays a crucial role in the question answering system, and it aim to accurately assign one or more labels to question based on expected answer type. Nonetheless, classifying user’s question is a very challenging task due to the flexibility of Natural Language where a question can be written in many different forms and information within the sentence may not be enough to effectively to classify the question. Limited researches have focused on question classification for Arabic question answering. In this research we used support vector machine (SVM) and pattern matching to classify question into three main classes which are “Who”, “Where” and “What”. The SVM leverage features such as n-gram and WordNet. The WordNet is used to map words in questions to their synonyms that have the same meaning. Five pattern were introduced to analyze “What” question and label the questions with “definition”, “person”, “location” or “object”. The dataset set used in this research consist of 200 question about Hadith from Sahih Al Bukhari. The experimental result scored F-measure at 95.2%, 84.6%, and 83.6% respectively for “Who”, “Where” and “What”. The result show that the SVM classifier is useful to classify question in Arabic language.

AB - Question classification plays a crucial role in the question answering system, and it aim to accurately assign one or more labels to question based on expected answer type. Nonetheless, classifying user’s question is a very challenging task due to the flexibility of Natural Language where a question can be written in many different forms and information within the sentence may not be enough to effectively to classify the question. Limited researches have focused on question classification for Arabic question answering. In this research we used support vector machine (SVM) and pattern matching to classify question into three main classes which are “Who”, “Where” and “What”. The SVM leverage features such as n-gram and WordNet. The WordNet is used to map words in questions to their synonyms that have the same meaning. Five pattern were introduced to analyze “What” question and label the questions with “definition”, “person”, “location” or “object”. The dataset set used in this research consist of 200 question about Hadith from Sahih Al Bukhari. The experimental result scored F-measure at 95.2%, 84.6%, and 83.6% respectively for “Who”, “Where” and “What”. The result show that the SVM classifier is useful to classify question in Arabic language.

KW - Machine learning

KW - Question classification system

UR - http://www.scopus.com/inward/record.url?scp=84969510011&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969510011&partnerID=8YFLogxK

M3 - Article

VL - 87

SP - 259

EP - 265

JO - Journal of Theoretical and Applied Information Technology

JF - Journal of Theoretical and Applied Information Technology

SN - 1992-8645

IS - 2

ER -