More Web Proxy on the site http://driver.im/

poster

Large-scale hierarchical text classification without labelled data

Authors:

Jean-Michel RendersAuthors Info & Claims

WSDM '11: Proceedings of the fourth ACM international conference on Web search and data mining

Pages 685 - 694

https://doi.org/10.1145/1935826.1935919

Published: 09 February 2011 Publication History

Abstract

The traditional machine learning approaches for text classification often require labelled data for learning classifiers. However, when applied to large-scale classification involving thousands of categories, creating such labelled data is extremely expensive since typically the data is manually labelled by humans. Motivated by this, we propose a novel approach for large-scale hierarchical text classification which does not require any labelled data. We explore a perspective where the meaning of a category is not defined by human-labelled documents, but by its description and more importantly its relationships with other categories (e.g. its ascendants and descendants). Specifically, we take advantage of the ontological knowledge in all phases of the whole process, namely when retrieving pseudo-labelled documents, when iteratively training the category models and when categorizing test documents. Our experiments based on a taxonomy containing 1131 categories and widely adopted in the news industry as a standard for the NewsML framework demonstrate the effectiveness of our approach in these phases both qualitatively and quantitatively. In particular, we emphasize that just by taking the simple ontological knowledge defined in the category hierarchy, we could automatically build a large-scale hierarchical classifier with reasonable performance of 67% in terms of the hierarchy-based F-1 measure.

References

[1]

H. Avancini, A. Lavelli, F. Sebastiani, and R. Zanoli. Automatic expansion of domain-specific lexicons by term categorization. ACM Transactions on Speech and Language Processing (TSLP) 3(1):1--30, 2006.

Digital Library

[2]

D. Blei, T. Griffiths, M. Jordan, and J. Tenenbaum. Hierarchical topic models and the nested chinese restaurant process. In Advances in Neural Information Processing Systems MIT Press, 2004.

[3]

D. Blei, A. Y. Ng, and M. Jordan. Latent dirichlet allocation. Journal of Machine Learning Research 3:993--1022, 2003.

Digital Library

[4]

E. Costa, A. Lorena, A. Carvalho, and A. Freitas. A review of performance evaluation measures for hierarchical classifiers. In Evaluation Methods for Machine Learning II: papers from the AAAI-2007 Workshop pages 1--6. AAAI Press, 2007.

[5]

A. A. Dayanik, D. D. Lewis, D. Madigan, V. Menkov, and A. Genkin. Constructing informative prior distributions from domain knowledge in text classification. In Proceedings of SIGIR pages 493--500. ACM Press, 2006.

Digital Library

[6]

S. Dumais. Hierarchical classification of web content. In Proceedings of SIGIR pages 256--263. ACM Press, 2000.

Digital Library

[7]

E. Gaussier, C. Goutte, K. Popat, and F. Chen. A hierarchical model for clustering and categorising documents. In Proceedings of ECIR 2002.

Digital Library

[8]

A. Gliozzo, C. Strapparava, and I. Dagan. Improving text categorization bootstrapping via unsupervised learning. ACM Transactions on Speech and Language Processing (TSLP) 6(1), 2009.

Digital Library

[9]

S. Godbole, A. Harpale, S. Sarawagi, and S. Chakrabarti. Document classification through interactive supervision of document and term labels. In Proceedings of PKDD pages 185--196, 2004.

Digital Library

[10]

T. Griffiths and M. Steyvers. Finding scientific topics. Proceedings of the National Academy of Sciences 101:5228--5235, 2004.

[11]

V. Ha-Thuc, Y. Mejova, C. Harris, and P. Srinivasan. News event modeling and tracking in the social web with ontological guidance. In Proceedings of IEEE International Conference on Semantic Computing 2010.

Digital Library

[12]

T. Hofmann. Probabilistic latent semantic analysis. In Proceedings of Uncertainty in Artificial Intelligence, 1999 pages 289--296, 1999.

Digital Library

[13]

C.-M. Hung and L.-F. Chien. Web-based text classification in the absence of manually labeled training documents. JASIST 58(1):88--96, 2007.

Digital Library

[14]

Y. Ko and J. Seo. Learning with unlabeled data for text categorization using bootstrapping and feature projection techniques. In Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics 2004.

Digital Library

[15]

D. Koller and M. Sahami. Hierarchically classifying documents using very few words. In Proceedings of ICML 1997.

Digital Library

[16]

A. Krithara, M. Amini, J. michel Renders, and C. Goutte. Semi-supervised document classification with a mislabeling error model. In Proceedings of ECIR 2008.

Digital Library

[17]

A. Mccallum and K. Nigam. Text classification by bootstrapping with keywords, em and shrinkage. In Workshop for Unsupervised Learning in Natural Language Processing pages 52--58, 1999.

[18]

A. Mccallum, R. Rosenfeld, T. Mitchell, and A. Ng. Improving text classification by shrinkage in a hierarchy of classes, 1998.

[19]

D. Mimno, W. Li, and A. McCallum. Mixtures of hierarchical topics with pachinko allocation. In Proceedings of ICML pages 633--640. ACM, 2007.

Digital Library

[20]

A. Sun and E.-P. Lim. Hierarchical text classification and evaluation. In Proceedings of ICDM 2001.

Digital Library

[21]

K. Toutanova and F. Chen. Text classification in a hierarchical mixture model for small training sets. In Proceedings of CIKM pages 105--113. ACM Press, 2001.

Digital Library

[22]

S. Veeramachaneni, D. Sona, and P. Avesani. Hierarchical dirichlet model for document classification. In Proceedings of ICML volume 119, pages 928--935. ACM, 2005.

Digital Library

[23]

P. Wang and C. Domeniconi. Towards a universal text classifier: Transfer learning using encyclopedic knowledge. In Proceedings of ICDM Workshops 2009.

Digital Library

[24]

R. Wetzker, T. Alpcan, C. Bauckhage, W. Umbrath, and S. Albayrak. An unsupervised hierarchical approach to document categorization. In Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence pages 52--58, 2007.

Digital Library

[25]

C. Zhang, G.-R. Xue, and Y. Yu. Knowledge supervised text classification with no labeled documents. In Proceedings of PRICAI Springer, 2008.

Digital Library

Cited By

Li DBi ZHan XQu ZLyu C(2024)Extracting key topics from massive COVID-19 information on social networks: An integrated deep learning and LDA frameworkHigh-Confidence Computing10.1016/j.hcc.2024.100213(100213)Online publication date: Feb-2024
https://doi.org/10.1016/j.hcc.2024.100213
Hagerman CBrath RLangevin S(2022)VisIRML: Visualization with an Interactive Information Retrieval and Machine Learning ClassifierIntegrating Artificial Intelligence and Visualization for Visual Knowledge Discovery10.1007/978-3-030-93119-3_13(337-357)Online publication date: 5-Jun-2022
https://doi.org/10.1007/978-3-030-93119-3_13
Pereira RCosta YSilla C(2021)Handling imbalance in hierarchical classification problems using local classifiers approachesData Mining and Knowledge Discovery10.1007/s10618-021-00762-835:4(1564-1621)Online publication date: 1-Jul-2021
https://dl.acm.org/doi/10.1007/s10618-021-00762-8
Show More Cited By

Index Terms

Large-scale hierarchical text classification without labelled data

Recommendations

Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification
WWW '19: The World Wide Web Conference

Hierarchical text classification has many real-world applications. However, labeling a large number of documents is costly. In practice, we can use semi-supervised learning or weakly supervised learning (e.g., dataless classification) to reduce the ...
Hierarchical text classification with multi-label contrastive learning and KNN
Abstract
Given the complicated label hierarchy, hierarchical text classification (HTC) has emerged as a challenging subtask in the realm of multi-label text classification. Existing methods enhance the quality of text representations by contrastive ...
Hierarchy-Aware and Label Balanced Model for Hierarchical Text Classification
Highlights
- Propose a hierarchy-aware and label balanced model based on the model HGCLR for hierarchical text classification.
- Propose a new method called multi-label negative supervision to obtain more hierarchy-aware text representations.
- ...
Abstract
Hierarchical text classification, where labels can be modeled as a hierarchical structure, is a special multi-label text classification sub-task. Current methods mainly improve model performance by modeling label dependencies. The model HGCLR ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

WSDM '11: Proceedings of the fourth ACM international conference on Web search and data mining

February 2011

870 pages

ISBN:9781450304931

DOI:10.1145/1935826

General Chair:
Irwin King
CUHK, Hong Kong
,
Program Chairs:
Wolfgang Nejdl
L3S and University of Hannover, Germany
,
Hang Li
Microsoft Research Asia, China

Copyright © 2011 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 09 February 2011

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Poster

Conference

WSDM'11

Sponsor:

WSDM'11: Fourth ACM International Conference on Web Search and Data Mining

February 9 - 12, 2011

Hong Kong, China

Acceptance Rates

WSDM '11 Paper Acceptance Rate 83 of 372 submissions, 22%;

Overall Acceptance Rate 498 of 2,863 submissions, 17%

Upcoming Conference

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

12
Total Citations
View Citations
616
Total Downloads

Downloads (Last 12 months)23
Downloads (Last 6 weeks)4

Reflects downloads up to 21 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Li DBi ZHan XQu ZLyu C(2024)Extracting key topics from massive COVID-19 information on social networks: An integrated deep learning and LDA frameworkHigh-Confidence Computing10.1016/j.hcc.2024.100213(100213)Online publication date: Feb-2024
https://doi.org/10.1016/j.hcc.2024.100213
Hagerman CBrath RLangevin S(2022)VisIRML: Visualization with an Interactive Information Retrieval and Machine Learning ClassifierIntegrating Artificial Intelligence and Visualization for Visual Knowledge Discovery10.1007/978-3-030-93119-3_13(337-357)Online publication date: 5-Jun-2022
https://doi.org/10.1007/978-3-030-93119-3_13
Pereira RCosta YSilla C(2021)Handling imbalance in hierarchical classification problems using local classifiers approachesData Mining and Knowledge Discovery10.1007/s10618-021-00762-835:4(1564-1621)Online publication date: 1-Jul-2021
https://dl.acm.org/doi/10.1007/s10618-021-00762-8
Hagerman CBrath RLangevin S(2019)Visual Analytic System for Subject Matter Expert Document Tagging using Information Retrieval and Semi-Supervised Machine Learning2019 23rd International Conference Information Visualisation (IV)10.1109/IV.2019.00047(234-240)Online publication date: Jul-2019
https://doi.org/10.1109/IV.2019.00047
Tao FZhang CChen XJiang MHanratty TKaplan LHan J(2018)Doc2Cube: Allocating Documents to Text Cube Without Labeled Data2018 IEEE International Conference on Data Mining (ICDM)10.1109/ICDM.2018.00169(1260-1265)Online publication date: Nov-2018
https://doi.org/10.1109/ICDM.2018.00169
Du YLiu JKe WGong X(2018)Hierarchy construction and text classification based on the relaxation strategy and least information modelExpert Systems with Applications: An International Journal10.1016/j.eswa.2018.02.003100:C(157-164)Online publication date: 15-Jun-2018
https://dl.acm.org/doi/10.1016/j.eswa.2018.02.003
Hingmire SChakraborti SPalshikar GSodani A(2017)WikiLDAProceedings of the 9th Knowledge Capture Conference10.1145/3148011.3154465(1-4)Online publication date: 4-Dec-2017
https://dl.acm.org/doi/10.1145/3148011.3154465
Dehghani MAzarbonyad HKamps JMarx MCarterette BFang HLalmas MNie J(2016)On Horizontal and Vertical Separation in Hierarchical Text ClassificationProceedings of the 2016 ACM International Conference on the Theory of Information Retrieval10.1145/2970398.2970408(185-194)Online publication date: 12-Sep-2016
https://dl.acm.org/doi/10.1145/2970398.2970408
Ko Y(2015)A new term-weighting scheme for text classification using the odds of positive and negative class probabilitiesJournal of the Association for Information Science and Technology10.1002/asi.2333866:12(2553-2565)Online publication date: 1-Dec-2015
https://dl.acm.org/doi/10.1002/asi.23338
Binh Tran GSchwabe DAlmeida VGlaser HBaeza-Yates RMoon S(2013)Structured summarization for news eventsProceedings of the 22nd International Conference on World Wide Web10.1145/2487788.2487940(343-348)Online publication date: 13-May-2013
https://dl.acm.org/doi/10.1145/2487788.2487940
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents