WikiKreator: Improvingwikipedia stubs automatically

Siddhartha Banerjee, Prasenjit Mitra

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

6 Citations (Scopus)

Abstract

Stubs onWikipedia often lack comprehensive information. The huge cost of editing Wikipedia and the presence of only a limited number of active contributors curb the consistent growth ofWikipedia. In this work, we present WikiKreator, a system that is capable of generating content automatically to improve existing stubs on Wikipedia. The system has two components. First, a text classifier built using topic distribution vectors is used to assign content from the web to various sections on a Wikipedia article. Second, we propose a novel abstractive summarization technique based on an optimization framework that generates section-specific summaries for Wikipedia stubs. Experiments show thatWikiKreator is capable of generating well-formed informative content. Further, automatically generated content from our system have been appended to Wikipedia stubs and the content has been retained successfully proving the effectiveness of our approach.

Original languageEnglish
Title of host publicationACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages867-877
Number of pages11
Volume1
ISBN (Print)9781941643723
Publication statusPublished - 2015
Event53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 - Beijing, China
Duration: 26 Jul 201531 Jul 2015

Other

Other53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015
CountryChina
CityBeijing
Period26/7/1531/7/15

Fingerprint

Curbs
Classifiers
Costs
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Banerjee, S., & Mitra, P. (2015). WikiKreator: Improvingwikipedia stubs automatically. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference (Vol. 1, pp. 867-877). Association for Computational Linguistics (ACL).

WikiKreator : Improvingwikipedia stubs automatically. / Banerjee, Siddhartha; Mitra, Prasenjit.

ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 1 Association for Computational Linguistics (ACL), 2015. p. 867-877.

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

Banerjee, S & Mitra, P 2015, WikiKreator: Improvingwikipedia stubs automatically. in ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. vol. 1, Association for Computational Linguistics (ACL), pp. 867-877, 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015, Beijing, China, 26/7/15.
Banerjee S, Mitra P. WikiKreator: Improvingwikipedia stubs automatically. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 1. Association for Computational Linguistics (ACL). 2015. p. 867-877
Banerjee, Siddhartha ; Mitra, Prasenjit. / WikiKreator : Improvingwikipedia stubs automatically. ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 1 Association for Computational Linguistics (ACL), 2015. pp. 867-877
@inproceedings{9c1b5ee25e0c4a85af9a43831ed693fe,
title = "WikiKreator: Improvingwikipedia stubs automatically",
abstract = "Stubs onWikipedia often lack comprehensive information. The huge cost of editing Wikipedia and the presence of only a limited number of active contributors curb the consistent growth ofWikipedia. In this work, we present WikiKreator, a system that is capable of generating content automatically to improve existing stubs on Wikipedia. The system has two components. First, a text classifier built using topic distribution vectors is used to assign content from the web to various sections on a Wikipedia article. Second, we propose a novel abstractive summarization technique based on an optimization framework that generates section-specific summaries for Wikipedia stubs. Experiments show thatWikiKreator is capable of generating well-formed informative content. Further, automatically generated content from our system have been appended to Wikipedia stubs and the content has been retained successfully proving the effectiveness of our approach.",
author = "Siddhartha Banerjee and Prasenjit Mitra",
year = "2015",
language = "English",
isbn = "9781941643723",
volume = "1",
pages = "867--877",
booktitle = "ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - WikiKreator

T2 - Improvingwikipedia stubs automatically

AU - Banerjee, Siddhartha

AU - Mitra, Prasenjit

PY - 2015

Y1 - 2015

N2 - Stubs onWikipedia often lack comprehensive information. The huge cost of editing Wikipedia and the presence of only a limited number of active contributors curb the consistent growth ofWikipedia. In this work, we present WikiKreator, a system that is capable of generating content automatically to improve existing stubs on Wikipedia. The system has two components. First, a text classifier built using topic distribution vectors is used to assign content from the web to various sections on a Wikipedia article. Second, we propose a novel abstractive summarization technique based on an optimization framework that generates section-specific summaries for Wikipedia stubs. Experiments show thatWikiKreator is capable of generating well-formed informative content. Further, automatically generated content from our system have been appended to Wikipedia stubs and the content has been retained successfully proving the effectiveness of our approach.

AB - Stubs onWikipedia often lack comprehensive information. The huge cost of editing Wikipedia and the presence of only a limited number of active contributors curb the consistent growth ofWikipedia. In this work, we present WikiKreator, a system that is capable of generating content automatically to improve existing stubs on Wikipedia. The system has two components. First, a text classifier built using topic distribution vectors is used to assign content from the web to various sections on a Wikipedia article. Second, we propose a novel abstractive summarization technique based on an optimization framework that generates section-specific summaries for Wikipedia stubs. Experiments show thatWikiKreator is capable of generating well-formed informative content. Further, automatically generated content from our system have been appended to Wikipedia stubs and the content has been retained successfully proving the effectiveness of our approach.

UR - http://www.scopus.com/inward/record.url?scp=84943802855&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943802855&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84943802855

SN - 9781941643723

VL - 1

SP - 867

EP - 877

BT - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -