Collective document classification with implicit inter-document semantic relationships

Clinton Burford; Steven Bird; Timothy Baldwin

Collective document classification with implicit inter-document semantic relationships

Clinton Burford, Steven Bird, Timothy Baldwin

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

Abstract

This paper addresses the question of how document classifiers can exploit implicit information about document similarity to improve document classifier accuracy. We infer document similarity using simple n-gram overlap, and demonstrate that this improves overall document classification performance over two datasets. As part of this, we find that collective classification based on simple iterative classifiers outperforms the more complex and computationally-intensive dual classifier approach.

Original language	English
Title of host publication	Proceedings of the 4th Joint Conference on Lexical and Computational Semantics (*SEM 2015)
Place of Publication	Denver, United States
Publisher	Association for Computational Linguistics (ACL)
Pages	106-116
Number of pages	11
ISBN (Electronic)	9781941643396
Publication status	Published - 1 Jan 2015
Externally published	Yes
Event	4th Joint Conference on Lexical and Computational Semantics, *SEM 2015 - Denver, United States Duration: 4 Jun 2015 → 5 Jun 2015

Conference

Conference	4th Joint Conference on Lexical and Computational Semantics, *SEM 2015
Country/Territory	United States
City	Denver
Period	4/06/15 → 5/06/15

Cite this

@inproceedings{67b70f9e8f6a4dc38668f4209c30a46a,

title = "Collective document classification with implicit inter-document semantic relationships",

abstract = "This paper addresses the question of how document classifiers can exploit implicit information about document similarity to improve document classifier accuracy. We infer document similarity using simple n-gram overlap, and demonstrate that this improves overall document classification performance over two datasets. As part of this, we find that collective classification based on simple iterative classifiers outperforms the more complex and computationally-intensive dual classifier approach.",

author = "Clinton Burford and Steven Bird and Timothy Baldwin",

year = "2015",

month = jan,

day = "1",

language = "English",

pages = "106--116",

booktitle = "Proceedings of the 4th Joint Conference on Lexical and Computational Semantics (*SEM 2015)",

publisher = "Association for Computational Linguistics (ACL)",

note = "4th Joint Conference on Lexical and Computational Semantics, *SEM 2015 ; Conference date: 04-06-2015 Through 05-06-2015",

}

Burford, C, Bird, S & Baldwin, T 2015, Collective document classification with implicit inter-document semantic relationships. in Proceedings of the 4th Joint Conference on Lexical and Computational Semantics (*SEM 2015). Association for Computational Linguistics (ACL), Denver, United States, pp. 106-116, 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015, Denver, United States, 4/06/15.

Collective document classification with implicit inter-document semantic relationships. / Burford, Clinton; Bird, Steven; Baldwin, Timothy.
Proceedings of the 4th Joint Conference on Lexical and Computational Semantics (*SEM 2015). Denver, United States: Association for Computational Linguistics (ACL), 2015. p. 106-116.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

TY - GEN

T1 - Collective document classification with implicit inter-document semantic relationships

AU - Burford, Clinton

AU - Bird, Steven

AU - Baldwin, Timothy

PY - 2015/1/1

Y1 - 2015/1/1

N2 - This paper addresses the question of how document classifiers can exploit implicit information about document similarity to improve document classifier accuracy. We infer document similarity using simple n-gram overlap, and demonstrate that this improves overall document classification performance over two datasets. As part of this, we find that collective classification based on simple iterative classifiers outperforms the more complex and computationally-intensive dual classifier approach.

AB - This paper addresses the question of how document classifiers can exploit implicit information about document similarity to improve document classifier accuracy. We infer document similarity using simple n-gram overlap, and demonstrate that this improves overall document classification performance over two datasets. As part of this, we find that collective classification based on simple iterative classifiers outperforms the more complex and computationally-intensive dual classifier approach.

UR - http://www.scopus.com/inward/record.url?scp=85036464883&partnerID=8YFLogxK

UR - https://sites.google.com/site/starsem2015/

M3 - Conference Paper published in Proceedings

AN - SCOPUS:85036464883

SP - 106

EP - 116

BT - Proceedings of the 4th Joint Conference on Lexical and Computational Semantics (*SEM 2015)

PB - Association for Computational Linguistics (ACL)

CY - Denver, United States

T2 - 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015

Y2 - 4 June 2015 through 5 June 2015

ER -

Collective document classification with implicit inter-document semantic relationships

Abstract

Conference

Other files and links

Fingerprint

Cite this