Finding News Citations for Wikipedia

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

Research Organisations

External Research Organisations

  • Heidelberg University
View graph of relations

Details

Original languageEnglish
Title of host publicationCIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery (ACM)
Pages337-346
Number of pages10
ISBN (electronic)9781450340731
Publication statusPublished - Oct 2016
Event25th ACM International Conference on Information and Knowledge Management, CIKM 2016 - Indianapolis, United States
Duration: 24 Oct 201628 Oct 2016

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings
Volume24-28-October-2016

Abstract

An important editing policy in Wikipedia is to provide citations for added statements in Wikipedia pages, where statements can be arbitrary pieces of text, ranging from a sentence to a paragraph. In many cases citations are either outdated or missing altogether. In this work we address the problem of finding and updating news citations for statements in entity pages. We propose a two-stage supervised approach for this problem. In the first step, we construct a classifier to find out whether statements need a news citation or other kinds of citations (web, book, journal, etc.). In the second step, we develop a news citation algorithm for Wikipedia statements, which recommends appropriate citations from a given news collection. Apart from IR techniques that use the statement to query the news collection, we also formalize three properties of an appropriate citation, namely: (i) the citation should entail the Wikipedia statement, (ii) the statement should be central to the citation, and (iii) the citation should be from an authoritative source. We perform an extensive evaluation of both steps, using 20 million articles from a real-world news collection. Our results are quite promising, and show that we can perform this task with high precision and at scale.

ASJC Scopus subject areas

Cite this

Finding News Citations for Wikipedia. / Fetahu, Besnik; Markert, Katja; Nejdl, Wolfgang et al.
CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Association for Computing Machinery (ACM), 2016. p. 337-346 (International Conference on Information and Knowledge Management, Proceedings; Vol. 24-28-October-2016).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Fetahu, B, Markert, K, Nejdl, W & Anand, A 2016, Finding News Citations for Wikipedia. in CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, vol. 24-28-October-2016, Association for Computing Machinery (ACM), pp. 337-346, 25th ACM International Conference on Information and Knowledge Management, CIKM 2016, Indianapolis, United States, 24 Oct 2016. https://doi.org/10.1145/2983323.2983808
Fetahu, B., Markert, K., Nejdl, W., & Anand, A. (2016). Finding News Citations for Wikipedia. In CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management (pp. 337-346). (International Conference on Information and Knowledge Management, Proceedings; Vol. 24-28-October-2016). Association for Computing Machinery (ACM). https://doi.org/10.1145/2983323.2983808
Fetahu B, Markert K, Nejdl W, Anand A. Finding News Citations for Wikipedia. In CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Association for Computing Machinery (ACM). 2016. p. 337-346. (International Conference on Information and Knowledge Management, Proceedings). doi: 10.1145/2983323.2983808
Fetahu, Besnik ; Markert, Katja ; Nejdl, Wolfgang et al. / Finding News Citations for Wikipedia. CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Association for Computing Machinery (ACM), 2016. pp. 337-346 (International Conference on Information and Knowledge Management, Proceedings).
Download
@inproceedings{8833098933af4199a0d511d16bbea423,
title = "Finding News Citations for Wikipedia",
abstract = "An important editing policy in Wikipedia is to provide citations for added statements in Wikipedia pages, where statements can be arbitrary pieces of text, ranging from a sentence to a paragraph. In many cases citations are either outdated or missing altogether. In this work we address the problem of finding and updating news citations for statements in entity pages. We propose a two-stage supervised approach for this problem. In the first step, we construct a classifier to find out whether statements need a news citation or other kinds of citations (web, book, journal, etc.). In the second step, we develop a news citation algorithm for Wikipedia statements, which recommends appropriate citations from a given news collection. Apart from IR techniques that use the statement to query the news collection, we also formalize three properties of an appropriate citation, namely: (i) the citation should entail the Wikipedia statement, (ii) the statement should be central to the citation, and (iii) the citation should be from an authoritative source. We perform an extensive evaluation of both steps, using 20 million articles from a real-world news collection. Our results are quite promising, and show that we can perform this task with high precision and at scale.",
author = "Besnik Fetahu and Katja Markert and Wolfgang Nejdl and Avishek Anand",
note = "Funding information: This work is funded by the ERC Advanced Grant ALEXANDRIA (grant no. 339233).; 25th ACM International Conference on Information and Knowledge Management, CIKM 2016 ; Conference date: 24-10-2016 Through 28-10-2016",
year = "2016",
month = oct,
doi = "10.1145/2983323.2983808",
language = "English",
series = "International Conference on Information and Knowledge Management, Proceedings",
publisher = "Association for Computing Machinery (ACM)",
pages = "337--346",
booktitle = "CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management",
address = "United States",

}

Download

TY - GEN

T1 - Finding News Citations for Wikipedia

AU - Fetahu, Besnik

AU - Markert, Katja

AU - Nejdl, Wolfgang

AU - Anand, Avishek

N1 - Funding information: This work is funded by the ERC Advanced Grant ALEXANDRIA (grant no. 339233).

PY - 2016/10

Y1 - 2016/10

N2 - An important editing policy in Wikipedia is to provide citations for added statements in Wikipedia pages, where statements can be arbitrary pieces of text, ranging from a sentence to a paragraph. In many cases citations are either outdated or missing altogether. In this work we address the problem of finding and updating news citations for statements in entity pages. We propose a two-stage supervised approach for this problem. In the first step, we construct a classifier to find out whether statements need a news citation or other kinds of citations (web, book, journal, etc.). In the second step, we develop a news citation algorithm for Wikipedia statements, which recommends appropriate citations from a given news collection. Apart from IR techniques that use the statement to query the news collection, we also formalize three properties of an appropriate citation, namely: (i) the citation should entail the Wikipedia statement, (ii) the statement should be central to the citation, and (iii) the citation should be from an authoritative source. We perform an extensive evaluation of both steps, using 20 million articles from a real-world news collection. Our results are quite promising, and show that we can perform this task with high precision and at scale.

AB - An important editing policy in Wikipedia is to provide citations for added statements in Wikipedia pages, where statements can be arbitrary pieces of text, ranging from a sentence to a paragraph. In many cases citations are either outdated or missing altogether. In this work we address the problem of finding and updating news citations for statements in entity pages. We propose a two-stage supervised approach for this problem. In the first step, we construct a classifier to find out whether statements need a news citation or other kinds of citations (web, book, journal, etc.). In the second step, we develop a news citation algorithm for Wikipedia statements, which recommends appropriate citations from a given news collection. Apart from IR techniques that use the statement to query the news collection, we also formalize three properties of an appropriate citation, namely: (i) the citation should entail the Wikipedia statement, (ii) the statement should be central to the citation, and (iii) the citation should be from an authoritative source. We perform an extensive evaluation of both steps, using 20 million articles from a real-world news collection. Our results are quite promising, and show that we can perform this task with high precision and at scale.

UR - http://www.scopus.com/inward/record.url?scp=84996490260&partnerID=8YFLogxK

U2 - 10.1145/2983323.2983808

DO - 10.1145/2983323.2983808

M3 - Conference contribution

AN - SCOPUS:84996490260

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 337

EP - 346

BT - CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management

PB - Association for Computing Machinery (ACM)

T2 - 25th ACM International Conference on Information and Knowledge Management, CIKM 2016

Y2 - 24 October 2016 through 28 October 2016

ER -

By the same author(s)