A novel topic model for automatic term extraction

Sujian Li; Jiwei Li; Tao Song; Wenjie Li; Baobao Chang

doi:10.1145/2484028.2484106

A novel topic model for automatic term extraction

Sujian Li
, Jiwei Li
, Tao Song
, Wenjie Li
, Baobao Chang

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

20 Citations (Scopus)

Abstract

Automatic term extraction (ATE) aims at extracting domain-specific terms from a corpus of a certain domain. Termhood is one essential measure for judging whether a phrase is a term. Previous researches on termhood mainly depend on the word frequency information. In this paper, we propose to compute termhood based on semantic representation of words. A novel topic model, namely i-SWB, is developed to map the domain corpus into a latent semantic space, which is composed of some general topics, a background topic and a documents-specific topic. Experiments on four domains demonstrate that our approach outperforms the state-of-the-art ATE approaches.

Original language	English
Title of host publication	SIGIR 2013 - Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval
Pages	885-888
Number of pages	4
DOIs	https://doi.org/10.1145/2484028.2484106
Publication status	Published - 2 Sept 2013
Event	36th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2013 - Dublin, Ireland Duration: 28 Jul 2013 → 1 Aug 2013

Conference

Conference	36th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2013
Country/Territory	Ireland
City	Dublin
Period	28/07/13 → 1/08/13

Keywords

Term extraction
Termhood
Topic model

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Information Systems

More information

10.1145/2484028.2484106

Cite this

@inproceedings{4d4edf904f264685b7e3a0842c03a78a,

title = "A novel topic model for automatic term extraction",

abstract = "Automatic term extraction (ATE) aims at extracting domain-specific terms from a corpus of a certain domain. Termhood is one essential measure for judging whether a phrase is a term. Previous researches on termhood mainly depend on the word frequency information. In this paper, we propose to compute termhood based on semantic representation of words. A novel topic model, namely i-SWB, is developed to map the domain corpus into a latent semantic space, which is composed of some general topics, a background topic and a documents-specific topic. Experiments on four domains demonstrate that our approach outperforms the state-of-the-art ATE approaches.",

keywords = "Term extraction, Termhood, Topic model",

author = "Sujian Li and Jiwei Li and Tao Song and Wenjie Li and Baobao Chang",

year = "2013",

month = sep,

day = "2",

doi = "10.1145/2484028.2484106",

language = "English",

isbn = "9781450320344",

pages = "885--888",

booktitle = "SIGIR 2013 - Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval",

note = "36th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2013 ; Conference date: 28-07-2013 Through 01-08-2013",

}

Li, S, Li, J, Song, T, Li, W & Chang, B 2013, A novel topic model for automatic term extraction. in SIGIR 2013 - Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 885-888, 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2013, Dublin, Ireland, 28/07/13. https://doi.org/10.1145/2484028.2484106

A novel topic model for automatic term extraction. / Li, Sujian; Li, Jiwei; Song, Tao et al.
SIGIR 2013 - Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2013. p. 885-888.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - A novel topic model for automatic term extraction

AU - Li, Sujian

AU - Li, Jiwei

AU - Song, Tao

AU - Li, Wenjie

AU - Chang, Baobao

PY - 2013/9/2

Y1 - 2013/9/2

N2 - Automatic term extraction (ATE) aims at extracting domain-specific terms from a corpus of a certain domain. Termhood is one essential measure for judging whether a phrase is a term. Previous researches on termhood mainly depend on the word frequency information. In this paper, we propose to compute termhood based on semantic representation of words. A novel topic model, namely i-SWB, is developed to map the domain corpus into a latent semantic space, which is composed of some general topics, a background topic and a documents-specific topic. Experiments on four domains demonstrate that our approach outperforms the state-of-the-art ATE approaches.

AB - Automatic term extraction (ATE) aims at extracting domain-specific terms from a corpus of a certain domain. Termhood is one essential measure for judging whether a phrase is a term. Previous researches on termhood mainly depend on the word frequency information. In this paper, we propose to compute termhood based on semantic representation of words. A novel topic model, namely i-SWB, is developed to map the domain corpus into a latent semantic space, which is composed of some general topics, a background topic and a documents-specific topic. Experiments on four domains demonstrate that our approach outperforms the state-of-the-art ATE approaches.

KW - Term extraction

KW - Termhood

KW - Topic model

UR - https://www.scopus.com/pages/publications/84883086326

U2 - 10.1145/2484028.2484106

DO - 10.1145/2484028.2484106

M3 - Conference article published in proceeding or book

SN - 9781450320344

SP - 885

EP - 888

BT - SIGIR 2013 - Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval

T2 - 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2013

Y2 - 28 July 2013 through 1 August 2013

ER -

A novel topic model for automatic term extraction

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this