Citation recommendation without author supervision

Qi He, Daniel Kifer, Jian Pei, Prasenjit Mitra, C. Lee Giles

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

58 Citations (Scopus)

Abstract

Automatic recommendation of citations for a manuscript is highly valuable for scholarly activities since it can substantially improve the efficiency and quality of literature search. The prior techniques placed a considerable burden on users, who were required to provide a representative bibliography or to mark passages where citations are needed. In this paper we present a system that considerably reduces this burden: a user simply inputs a query manuscript (without a bibliography) and our system automatically finds locations where citations are needed. We show that naïve approaches do not work well due to massive noise in the document corpus. We produce a successful approach by carefully examining the relevance between segments in a query manuscript and the representative segments extracted from a document corpus. An extensive empirical evaluation using the CiteSeerX data set shows that our approach is effective.

Original languageEnglish
Title of host publicationProceedings of the 4th ACM International Conference on Web Search and Data Mining, WSDM 2011
Pages755-764
Number of pages10
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event4th ACM International Conference on Web Search and Data Mining, WSDM 2011 - Hong Kong, China
Duration: 9 Feb 201112 Feb 2011

Other

Other4th ACM International Conference on Web Search and Data Mining, WSDM 2011
CountryChina
CityHong Kong
Period9/2/1112/2/11

Fingerprint

Bibliographies

Keywords

  • Bibliometrics
  • Context
  • Extraction
  • Recommender systems

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Software

Cite this

He, Q., Kifer, D., Pei, J., Mitra, P., & Lee Giles, C. (2011). Citation recommendation without author supervision. In Proceedings of the 4th ACM International Conference on Web Search and Data Mining, WSDM 2011 (pp. 755-764) https://doi.org/10.1145/1935826.1935926

Citation recommendation without author supervision. / He, Qi; Kifer, Daniel; Pei, Jian; Mitra, Prasenjit; Lee Giles, C.

Proceedings of the 4th ACM International Conference on Web Search and Data Mining, WSDM 2011. 2011. p. 755-764.

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

He, Q, Kifer, D, Pei, J, Mitra, P & Lee Giles, C 2011, Citation recommendation without author supervision. in Proceedings of the 4th ACM International Conference on Web Search and Data Mining, WSDM 2011. pp. 755-764, 4th ACM International Conference on Web Search and Data Mining, WSDM 2011, Hong Kong, China, 9/2/11. https://doi.org/10.1145/1935826.1935926
He Q, Kifer D, Pei J, Mitra P, Lee Giles C. Citation recommendation without author supervision. In Proceedings of the 4th ACM International Conference on Web Search and Data Mining, WSDM 2011. 2011. p. 755-764 https://doi.org/10.1145/1935826.1935926
He, Qi ; Kifer, Daniel ; Pei, Jian ; Mitra, Prasenjit ; Lee Giles, C. / Citation recommendation without author supervision. Proceedings of the 4th ACM International Conference on Web Search and Data Mining, WSDM 2011. 2011. pp. 755-764
@inproceedings{ca090da956614fe782a64d97a869650f,
title = "Citation recommendation without author supervision",
abstract = "Automatic recommendation of citations for a manuscript is highly valuable for scholarly activities since it can substantially improve the efficiency and quality of literature search. The prior techniques placed a considerable burden on users, who were required to provide a representative bibliography or to mark passages where citations are needed. In this paper we present a system that considerably reduces this burden: a user simply inputs a query manuscript (without a bibliography) and our system automatically finds locations where citations are needed. We show that na{\"i}ve approaches do not work well due to massive noise in the document corpus. We produce a successful approach by carefully examining the relevance between segments in a query manuscript and the representative segments extracted from a document corpus. An extensive empirical evaluation using the CiteSeerX data set shows that our approach is effective.",
keywords = "Bibliometrics, Context, Extraction, Recommender systems",
author = "Qi He and Daniel Kifer and Jian Pei and Prasenjit Mitra and {Lee Giles}, C.",
year = "2011",
doi = "10.1145/1935826.1935926",
language = "English",
isbn = "9781450304931",
pages = "755--764",
booktitle = "Proceedings of the 4th ACM International Conference on Web Search and Data Mining, WSDM 2011",

}

TY - GEN

T1 - Citation recommendation without author supervision

AU - He, Qi

AU - Kifer, Daniel

AU - Pei, Jian

AU - Mitra, Prasenjit

AU - Lee Giles, C.

PY - 2011

Y1 - 2011

N2 - Automatic recommendation of citations for a manuscript is highly valuable for scholarly activities since it can substantially improve the efficiency and quality of literature search. The prior techniques placed a considerable burden on users, who were required to provide a representative bibliography or to mark passages where citations are needed. In this paper we present a system that considerably reduces this burden: a user simply inputs a query manuscript (without a bibliography) and our system automatically finds locations where citations are needed. We show that naïve approaches do not work well due to massive noise in the document corpus. We produce a successful approach by carefully examining the relevance between segments in a query manuscript and the representative segments extracted from a document corpus. An extensive empirical evaluation using the CiteSeerX data set shows that our approach is effective.

AB - Automatic recommendation of citations for a manuscript is highly valuable for scholarly activities since it can substantially improve the efficiency and quality of literature search. The prior techniques placed a considerable burden on users, who were required to provide a representative bibliography or to mark passages where citations are needed. In this paper we present a system that considerably reduces this burden: a user simply inputs a query manuscript (without a bibliography) and our system automatically finds locations where citations are needed. We show that naïve approaches do not work well due to massive noise in the document corpus. We produce a successful approach by carefully examining the relevance between segments in a query manuscript and the representative segments extracted from a document corpus. An extensive empirical evaluation using the CiteSeerX data set shows that our approach is effective.

KW - Bibliometrics

KW - Context

KW - Extraction

KW - Recommender systems

UR - http://www.scopus.com/inward/record.url?scp=79952384357&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952384357&partnerID=8YFLogxK

U2 - 10.1145/1935826.1935926

DO - 10.1145/1935826.1935926

M3 - Conference contribution

AN - SCOPUS:79952384357

SN - 9781450304931

SP - 755

EP - 764

BT - Proceedings of the 4th ACM International Conference on Web Search and Data Mining, WSDM 2011

ER -