Utilizing context in generative bayesian models for linked corpus

Saurabh Kataria, Prasenjit Mitra, Sumit Bhatia

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

20 Citations (Scopus)

Abstract

In an interlinked corpus of documents, the context in which a citation appears provides extra information about the cited document. However, associating terms in the context to the cited document remains an open problem. We propose a novel document generation approach that statistically incor porates the context in which a document links to another doc ument. We quantitatively show that the proposed generation scheme explains the linking phenomenon better than previous approaches. The context information along with the actual content of the document provides signicant improvements over the previous approaches for various real world evalua tion tasks such as link prediction and log-likelihood estima tion on unseen content. The proposed method is more scal able to large collection of documents compared to the previ ous approaches.

Original languageEnglish
Title of host publicationProceedings of the National Conference on Artificial Intelligence
Pages1340-1345
Number of pages6
Volume3
Publication statusPublished - 2010
Externally publishedYes
Event24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference, AAAI-10 / IAAI-10 - Atlanta, GA
Duration: 11 Jul 201015 Jul 2010

Other

Other24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference, AAAI-10 / IAAI-10
CityAtlanta, GA
Period11/7/1015/7/10

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Kataria, S., Mitra, P., & Bhatia, S. (2010). Utilizing context in generative bayesian models for linked corpus. In Proceedings of the National Conference on Artificial Intelligence (Vol. 3, pp. 1340-1345)

Utilizing context in generative bayesian models for linked corpus. / Kataria, Saurabh; Mitra, Prasenjit; Bhatia, Sumit.

Proceedings of the National Conference on Artificial Intelligence. Vol. 3 2010. p. 1340-1345.

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

Kataria, S, Mitra, P & Bhatia, S 2010, Utilizing context in generative bayesian models for linked corpus. in Proceedings of the National Conference on Artificial Intelligence. vol. 3, pp. 1340-1345, 24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference, AAAI-10 / IAAI-10, Atlanta, GA, 11/7/10.
Kataria S, Mitra P, Bhatia S. Utilizing context in generative bayesian models for linked corpus. In Proceedings of the National Conference on Artificial Intelligence. Vol. 3. 2010. p. 1340-1345
Kataria, Saurabh ; Mitra, Prasenjit ; Bhatia, Sumit. / Utilizing context in generative bayesian models for linked corpus. Proceedings of the National Conference on Artificial Intelligence. Vol. 3 2010. pp. 1340-1345
@inproceedings{46eb76ae4bf841bfbd05e1780f9611e5,
title = "Utilizing context in generative bayesian models for linked corpus",
abstract = "In an interlinked corpus of documents, the context in which a citation appears provides extra information about the cited document. However, associating terms in the context to the cited document remains an open problem. We propose a novel document generation approach that statistically incor porates the context in which a document links to another doc ument. We quantitatively show that the proposed generation scheme explains the linking phenomenon better than previous approaches. The context information along with the actual content of the document provides signicant improvements over the previous approaches for various real world evalua tion tasks such as link prediction and log-likelihood estima tion on unseen content. The proposed method is more scal able to large collection of documents compared to the previ ous approaches.",
author = "Saurabh Kataria and Prasenjit Mitra and Sumit Bhatia",
year = "2010",
language = "English",
isbn = "9781577354666",
volume = "3",
pages = "1340--1345",
booktitle = "Proceedings of the National Conference on Artificial Intelligence",

}

TY - GEN

T1 - Utilizing context in generative bayesian models for linked corpus

AU - Kataria, Saurabh

AU - Mitra, Prasenjit

AU - Bhatia, Sumit

PY - 2010

Y1 - 2010

N2 - In an interlinked corpus of documents, the context in which a citation appears provides extra information about the cited document. However, associating terms in the context to the cited document remains an open problem. We propose a novel document generation approach that statistically incor porates the context in which a document links to another doc ument. We quantitatively show that the proposed generation scheme explains the linking phenomenon better than previous approaches. The context information along with the actual content of the document provides signicant improvements over the previous approaches for various real world evalua tion tasks such as link prediction and log-likelihood estima tion on unseen content. The proposed method is more scal able to large collection of documents compared to the previ ous approaches.

AB - In an interlinked corpus of documents, the context in which a citation appears provides extra information about the cited document. However, associating terms in the context to the cited document remains an open problem. We propose a novel document generation approach that statistically incor porates the context in which a document links to another doc ument. We quantitatively show that the proposed generation scheme explains the linking phenomenon better than previous approaches. The context information along with the actual content of the document provides signicant improvements over the previous approaches for various real world evalua tion tasks such as link prediction and log-likelihood estima tion on unseen content. The proposed method is more scal able to large collection of documents compared to the previ ous approaches.

UR - http://www.scopus.com/inward/record.url?scp=77958607310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77958607310&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781577354666

VL - 3

SP - 1340

EP - 1345

BT - Proceedings of the National Conference on Artificial Intelligence

ER -