A CNN based approach to Phrase-Labelling through classification of N-Grams

Chinmay Choudhary; Colm O’Riordan

doi:10.1145/3368567.3368571

A CNN based approach to Phrase-Labelling through classification of N-Grams

Chinmay Choudhary, Colm O’Riordan

Computer Science

University of Galway

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

Abstract

Modern approaches address the task of Phrase-labelling within any input sentence (eg: NER, Chunking etc.) as a variant of word-tagging problem. These approaches extract the desired phrases as word-sequences which are mapped to specific tag-sequences (with Begin, Intermediate and End tag-types). However we argue that basic nature of Phrase-labelling is not temporal but spatial in nature. Thus we propose and test the hypothesis that a CNN based model that directly extracts labelled n-grams from the input sentence would outperform standard RNN based model.

Original language	English
Title of host publication	FIRE 2019 - Proceedings of the 11th annual meeting of the Forum for Information Retrieval Evaluation
Editors	Prasenjit Majumder, Mandar Mitra, Surupendu Gangopadhyay, Parth Mehta
Publisher	Association for Computing Machinery
Pages	18-23
Number of pages	6
ISBN (Electronic)	9781450377508
DOIs	https://doi.org/10.1145/3368567.3368571
Publication status	Published - 12 Dec 2019
Event	11th Annual Meeting of the Forum for Information Retrieval Evaluation, FIRE 2019 - Kolkata, India Duration: 12 Dec 2019 → 15 Dec 2019

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	11th Annual Meeting of the Forum for Information Retrieval Evaluation, FIRE 2019
Country/Territory	India
City	Kolkata
Period	12/12/19 → 15/12/19

Keywords

Convolutional Neural Networks
Information Retrieval
NLP
Phrase-labelling

Access to Document

10.1145/3368567.3368571

Cite this

Choudhary, C., & O’Riordan, C. (2019). A CNN based approach to Phrase-Labelling through classification of N-Grams. In P. Majumder, M. Mitra, S. Gangopadhyay, & P. Mehta (Eds.), FIRE 2019 - Proceedings of the 11th annual meeting of the Forum for Information Retrieval Evaluation (pp. 18-23). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3368567.3368571

Choudhary, Chinmay ; O’Riordan, Colm. / A CNN based approach to Phrase-Labelling through classification of N-Grams. FIRE 2019 - Proceedings of the 11th annual meeting of the Forum for Information Retrieval Evaluation. editor / Prasenjit Majumder ; Mandar Mitra ; Surupendu Gangopadhyay ; Parth Mehta. Association for Computing Machinery, 2019. pp. 18-23 (ACM International Conference Proceeding Series).

@inproceedings{5344a590c4a34c779747b1ac88ef17ca,

title = "A CNN based approach to Phrase-Labelling through classification of N-Grams",

abstract = "Modern approaches address the task of Phrase-labelling within any input sentence (eg: NER, Chunking etc.) as a variant of word-tagging problem. These approaches extract the desired phrases as word-sequences which are mapped to specific tag-sequences (with Begin, Intermediate and End tag-types). However we argue that basic nature of Phrase-labelling is not temporal but spatial in nature. Thus we propose and test the hypothesis that a CNN based model that directly extracts labelled n-grams from the input sentence would outperform standard RNN based model.",

keywords = "Convolutional Neural Networks, Information Retrieval, NLP, Phrase-labelling",

author = "Chinmay Choudhary and Colm O{\textquoteright}Riordan",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 11th Annual Meeting of the Forum for Information Retrieval Evaluation, FIRE 2019 ; Conference date: 12-12-2019 Through 15-12-2019",

year = "2019",

month = dec,

day = "12",

doi = "10.1145/3368567.3368571",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = " Association for Computing Machinery",

pages = "18--23",

editor = "Prasenjit Majumder and Mandar Mitra and Surupendu Gangopadhyay and Parth Mehta",

booktitle = "FIRE 2019 - Proceedings of the 11th annual meeting of the Forum for Information Retrieval Evaluation",

}

Choudhary, C & O’Riordan, C 2019, A CNN based approach to Phrase-Labelling through classification of N-Grams. in P Majumder, M Mitra, S Gangopadhyay & P Mehta (eds), FIRE 2019 - Proceedings of the 11th annual meeting of the Forum for Information Retrieval Evaluation. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 18-23, 11th Annual Meeting of the Forum for Information Retrieval Evaluation, FIRE 2019, Kolkata, India, 12/12/19. https://doi.org/10.1145/3368567.3368571

A CNN based approach to Phrase-Labelling through classification of N-Grams. / Choudhary, Chinmay; O’Riordan, Colm.
FIRE 2019 - Proceedings of the 11th annual meeting of the Forum for Information Retrieval Evaluation. ed. / Prasenjit Majumder; Mandar Mitra; Surupendu Gangopadhyay; Parth Mehta. Association for Computing Machinery, 2019. p. 18-23 (ACM International Conference Proceeding Series).

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

TY - GEN

T1 - A CNN based approach to Phrase-Labelling through classification of N-Grams

AU - Choudhary, Chinmay

AU - O’Riordan, Colm

PY - 2019/12/12

Y1 - 2019/12/12

N2 - Modern approaches address the task of Phrase-labelling within any input sentence (eg: NER, Chunking etc.) as a variant of word-tagging problem. These approaches extract the desired phrases as word-sequences which are mapped to specific tag-sequences (with Begin, Intermediate and End tag-types). However we argue that basic nature of Phrase-labelling is not temporal but spatial in nature. Thus we propose and test the hypothesis that a CNN based model that directly extracts labelled n-grams from the input sentence would outperform standard RNN based model.

AB - Modern approaches address the task of Phrase-labelling within any input sentence (eg: NER, Chunking etc.) as a variant of word-tagging problem. These approaches extract the desired phrases as word-sequences which are mapped to specific tag-sequences (with Begin, Intermediate and End tag-types). However we argue that basic nature of Phrase-labelling is not temporal but spatial in nature. Thus we propose and test the hypothesis that a CNN based model that directly extracts labelled n-grams from the input sentence would outperform standard RNN based model.

KW - Convolutional Neural Networks

KW - Information Retrieval

KW - NLP

KW - Phrase-labelling

UR - http://www.scopus.com/inward/record.url?scp=85077517227&partnerID=8YFLogxK

U2 - 10.1145/3368567.3368571

DO - 10.1145/3368567.3368571

M3 - Conference Publication

T3 - ACM International Conference Proceeding Series

SP - 18

EP - 23

BT - FIRE 2019 - Proceedings of the 11th annual meeting of the Forum for Information Retrieval Evaluation

A2 - Majumder, Prasenjit

A2 - Mitra, Mandar

A2 - Gangopadhyay, Surupendu

A2 - Mehta, Parth

PB - Association for Computing Machinery

T2 - 11th Annual Meeting of the Forum for Information Retrieval Evaluation, FIRE 2019

Y2 - 12 December 2019 through 15 December 2019

ER -

Choudhary C, O’Riordan C. A CNN based approach to Phrase-Labelling through classification of N-Grams. In Majumder P, Mitra M, Gangopadhyay S, Mehta P, editors, FIRE 2019 - Proceedings of the 11th annual meeting of the Forum for Information Retrieval Evaluation. Association for Computing Machinery. 2019. p. 18-23. (ACM International Conference Proceeding Series). doi: 10.1145/3368567.3368571

A CNN based approach to Phrase-Labelling through classification of N-Grams

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this