Modeling topic dependencies in hierarchical text categorization

Alessandro Moschitti, Qi Ju, Richard Johansson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In this paper, we encode topic dependencies in hierarchical multi-label Text Categorization (TC) by means of rerankers. We represent reranking hypotheses with several innovative kernels considering both the structure of the hierarchy and the probability of nodes. Additionally, to better investigate the role of category relationships, we consider two interesting cases: (i) traditional schemes in which node-fathers include all the documents of their child-categories; and (ii) more general schemes, in which children can include documents not belonging to their fathers. The extensive experimentation on Reuters Corpus Volume 1 shows that our rerankers inject effective structural semantic dependencies in multi-classifiers and significantly outperform the state-of-the-art.

Original languageEnglish
Title of host publication50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference
Pages759-767
Number of pages9
Volume1
Publication statusPublished - 1 Dec 2012
Externally publishedYes
Event50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Jeju Island, Korea, Republic of
Duration: 8 Jul 201214 Jul 2012

Other

Other50th Annual Meeting of the Association for Computational Linguistics, ACL 2012
CountryKorea, Republic of
CityJeju Island
Period8/7/1214/7/12

Fingerprint

Labels
Classifiers
Semantics

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Software

Cite this

Moschitti, A., Ju, Q., & Johansson, R. (2012). Modeling topic dependencies in hierarchical text categorization. In 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference (Vol. 1, pp. 759-767)

Modeling topic dependencies in hierarchical text categorization. / Moschitti, Alessandro; Ju, Qi; Johansson, Richard.

50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. Vol. 1 2012. p. 759-767.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Moschitti, A, Ju, Q & Johansson, R 2012, Modeling topic dependencies in hierarchical text categorization. in 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. vol. 1, pp. 759-767, 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012, Jeju Island, Korea, Republic of, 8/7/12.
Moschitti A, Ju Q, Johansson R. Modeling topic dependencies in hierarchical text categorization. In 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. Vol. 1. 2012. p. 759-767
Moschitti, Alessandro ; Ju, Qi ; Johansson, Richard. / Modeling topic dependencies in hierarchical text categorization. 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. Vol. 1 2012. pp. 759-767
@inproceedings{dd7c675433514356b9ba5692b7d792d9,
title = "Modeling topic dependencies in hierarchical text categorization",
abstract = "In this paper, we encode topic dependencies in hierarchical multi-label Text Categorization (TC) by means of rerankers. We represent reranking hypotheses with several innovative kernels considering both the structure of the hierarchy and the probability of nodes. Additionally, to better investigate the role of category relationships, we consider two interesting cases: (i) traditional schemes in which node-fathers include all the documents of their child-categories; and (ii) more general schemes, in which children can include documents not belonging to their fathers. The extensive experimentation on Reuters Corpus Volume 1 shows that our rerankers inject effective structural semantic dependencies in multi-classifiers and significantly outperform the state-of-the-art.",
author = "Alessandro Moschitti and Qi Ju and Richard Johansson",
year = "2012",
month = "12",
day = "1",
language = "English",
isbn = "9781937284244",
volume = "1",
pages = "759--767",
booktitle = "50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference",

}

TY - GEN

T1 - Modeling topic dependencies in hierarchical text categorization

AU - Moschitti, Alessandro

AU - Ju, Qi

AU - Johansson, Richard

PY - 2012/12/1

Y1 - 2012/12/1

N2 - In this paper, we encode topic dependencies in hierarchical multi-label Text Categorization (TC) by means of rerankers. We represent reranking hypotheses with several innovative kernels considering both the structure of the hierarchy and the probability of nodes. Additionally, to better investigate the role of category relationships, we consider two interesting cases: (i) traditional schemes in which node-fathers include all the documents of their child-categories; and (ii) more general schemes, in which children can include documents not belonging to their fathers. The extensive experimentation on Reuters Corpus Volume 1 shows that our rerankers inject effective structural semantic dependencies in multi-classifiers and significantly outperform the state-of-the-art.

AB - In this paper, we encode topic dependencies in hierarchical multi-label Text Categorization (TC) by means of rerankers. We represent reranking hypotheses with several innovative kernels considering both the structure of the hierarchy and the probability of nodes. Additionally, to better investigate the role of category relationships, we consider two interesting cases: (i) traditional schemes in which node-fathers include all the documents of their child-categories; and (ii) more general schemes, in which children can include documents not belonging to their fathers. The extensive experimentation on Reuters Corpus Volume 1 shows that our rerankers inject effective structural semantic dependencies in multi-classifiers and significantly outperform the state-of-the-art.

UR - http://www.scopus.com/inward/record.url?scp=84878213949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878213949&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84878213949

SN - 9781937284244

VL - 1

SP - 759

EP - 767

BT - 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference

ER -