High Accuracy Rule-based Question Classification using Question Syntax and Semantics

Harish Tayyar Madabushi; Mark Lee

High Accuracy Rule-based Question Classification using Question Syntax and Semantics

Harish Tayyar Madabushi, Mark Lee

Computer Science

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

17 Citations (Scopus)

172 Downloads (Pure)

Abstract

We present in this paper a purely rule-based system for Question Classification which we divide into two parts: The first is the extraction of relevant words from a question by use of its structure, and the second is the classification of questions based on rules that associate these words to Concepts. We achieve an accuracy of 97.2%, close to a 6 point improvement over the previous State of the Art of 91.6%. Additionally, we believe that machine learning algorithms can be applied on top of this method to further improve accuracy.

Original language	English
Title of host publication	26th International Conference on Computational Linguistics (COLING 2016)
Publisher	Association for Computational Linguistics, ACL
Pages	1220-1230
Number of pages	11
ISBN (Print)	978-4-87974-702-0
Publication status	Published - 16 Dec 2016
Event	26th International Conference on Computational Linguistics (COLING 2016) - Osaka, Japan Duration: 11 Dec 2016 → 16 Dec 2016

Conference

Conference	26th International Conference on Computational Linguistics (COLING 2016)
Country/Territory	Japan
City	Osaka
Period	11/12/16 → 16/12/16

Access to Document

271_PaperAccepted author manuscript, 223 KB

Cite this

@inproceedings{eeb0708451d04e03a4239c2fe042b456,

title = "High Accuracy Rule-based Question Classification using Question Syntax and Semantics",

abstract = "We present in this paper a purely rule-based system for Question Classification which we divide into two parts: The first is the extraction of relevant words from a question by use of its structure, and the second is the classification of questions based on rules that associate these words to Concepts. We achieve an accuracy of 97.2%, close to a 6 point improvement over the previous State of the Art of 91.6%. Additionally, we believe that machine learning algorithms can be applied on top of this method to further improve accuracy.",

author = "{Tayyar Madabushi}, Harish and Mark Lee",

year = "2016",

month = dec,

day = "16",

language = "English",

isbn = "978-4-87974-702-0",

pages = "1220--1230",

booktitle = "26th International Conference on Computational Linguistics (COLING 2016)",

publisher = "Association for Computational Linguistics, ACL",

note = "26th International Conference on Computational Linguistics (COLING 2016) ; Conference date: 11-12-2016 Through 16-12-2016",

}

Tayyar Madabushi, H & Lee, M 2016, High Accuracy Rule-based Question Classification using Question Syntax and Semantics. in 26th International Conference on Computational Linguistics (COLING 2016). Association for Computational Linguistics, ACL, pp. 1220-1230, 26th International Conference on Computational Linguistics (COLING 2016), Osaka, Japan, 11/12/16. <http://coling2016.anlp.jp/doc/main.pdf>

TY - GEN

T1 - High Accuracy Rule-based Question Classification using Question Syntax and Semantics

AU - Tayyar Madabushi, Harish

AU - Lee, Mark

PY - 2016/12/16

Y1 - 2016/12/16

N2 - We present in this paper a purely rule-based system for Question Classification which we divide into two parts: The first is the extraction of relevant words from a question by use of its structure, and the second is the classification of questions based on rules that associate these words to Concepts. We achieve an accuracy of 97.2%, close to a 6 point improvement over the previous State of the Art of 91.6%. Additionally, we believe that machine learning algorithms can be applied on top of this method to further improve accuracy.

AB - We present in this paper a purely rule-based system for Question Classification which we divide into two parts: The first is the extraction of relevant words from a question by use of its structure, and the second is the classification of questions based on rules that associate these words to Concepts. We achieve an accuracy of 97.2%, close to a 6 point improvement over the previous State of the Art of 91.6%. Additionally, we believe that machine learning algorithms can be applied on top of this method to further improve accuracy.

M3 - Conference contribution

SN - 978-4-87974-702-0

SP - 1220

EP - 1230

BT - 26th International Conference on Computational Linguistics (COLING 2016)

PB - Association for Computational Linguistics, ACL

T2 - 26th International Conference on Computational Linguistics (COLING 2016)

Y2 - 11 December 2016 through 16 December 2016

ER -

High Accuracy Rule-based Question Classification using Question Syntax and Semantics

Abstract

Conference

Access to Document

Fingerprint

Cite this