Collective document classification with implicit inter-document semantic relationships

Clinton Burford, Steven Bird, Timothy Baldwin

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in Proceedings

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 languageEnglish
Title of host publicationProceedings of the 4th Joint Conference on Lexical and Computational Semantics (*SEM 2015)
Place of PublicationDenver, United States
PublisherAssociation for Computational Linguistics (ACL)
Pages106-116
Number of pages11
ISBN (Electronic)9781941643396
Publication statusPublished - 1 Jan 2015
Externally publishedYes
Event4th Joint Conference on Lexical and Computational Semantics, *SEM 2015 - Denver, United States
Duration: 4 Jun 20155 Jun 2015

Conference

Conference4th Joint Conference on Lexical and Computational Semantics, *SEM 2015
CountryUnited States
CityDenver
Period4/06/155/06/15

Fingerprint Dive into the research topics of 'Collective document classification with implicit inter-document semantic relationships'. Together they form a unique fingerprint.

Cite this