Learning from negative examples in set-expansion

Prateek Jindal; Dan Roth

doi:10.1109/ICDM.2011.86

Learning from negative examples in set-expansion

Prateek Jindal, Dan Roth

Siebel School of Computing and Data Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper addresses the task of set-expansion on free text. Set-expansion has been viewed as a problem of generating an extensive list of instances of a concept of interest, given a few examples of the concept as input. Our key contribution is that we show that the concept definition can be significantly improved by specifying some negative examples in the input, along with the positive examples. The state-of-the art centroid-based approach to set-expansion doesn't readily admit the negative examples. We develop an inference-based approach to set-expansion which naturally allows for negative examples and show that it performs significantly better than a strong baseline.

Original language	English (US)
Title of host publication	Proceedings - 11th IEEE International Conference on Data Mining, ICDM 2011
Pages	1110-1115
Number of pages	6
DOIs	https://doi.org/10.1109/ICDM.2011.86
State	Published - 2011
Event	11th IEEE International Conference on Data Mining, ICDM 2011 - Vancouver, BC, Canada Duration: Dec 11 2011 → Dec 14 2011

Publication series

Name	Proceedings - IEEE International Conference on Data Mining, ICDM
ISSN (Print)	1550-4786

Other

Other	11th IEEE International Conference on Data Mining, ICDM 2011
Country/Territory	Canada
City	Vancouver, BC
Period	12/11/11 → 12/14/11

ASJC Scopus subject areas

General Engineering

Online availability

10.1109/ICDM.2011.86

Library availability

Discover UIUC Full Text

Cite this

Jindal, P & Roth, D 2011, Learning from negative examples in set-expansion. in Proceedings - 11th IEEE International Conference on Data Mining, ICDM 2011., 6137323, Proceedings - IEEE International Conference on Data Mining, ICDM, pp. 1110-1115, 11th IEEE International Conference on Data Mining, ICDM 2011, Vancouver, BC, Canada, 12/11/11. https://doi.org/10.1109/ICDM.2011.86

@inproceedings{0dbcecc96b2243d58a4073f2ae0b671c,

title = "Learning from negative examples in set-expansion",

abstract = "This paper addresses the task of set-expansion on free text. Set-expansion has been viewed as a problem of generating an extensive list of instances of a concept of interest, given a few examples of the concept as input. Our key contribution is that we show that the concept definition can be significantly improved by specifying some negative examples in the input, along with the positive examples. The state-of-the art centroid-based approach to set-expansion doesn't readily admit the negative examples. We develop an inference-based approach to set-expansion which naturally allows for negative examples and show that it performs significantly better than a strong baseline.",

author = "Prateek Jindal and Dan Roth",

year = "2011",

doi = "10.1109/ICDM.2011.86",

language = "English (US)",

isbn = "9780769544083",

series = "Proceedings - IEEE International Conference on Data Mining, ICDM",

pages = "1110--1115",

booktitle = "Proceedings - 11th IEEE International Conference on Data Mining, ICDM 2011",

note = "11th IEEE International Conference on Data Mining, ICDM 2011 ; Conference date: 11-12-2011 Through 14-12-2011",

}

TY - GEN

T1 - Learning from negative examples in set-expansion

AU - Jindal, Prateek

AU - Roth, Dan

PY - 2011

Y1 - 2011

N2 - This paper addresses the task of set-expansion on free text. Set-expansion has been viewed as a problem of generating an extensive list of instances of a concept of interest, given a few examples of the concept as input. Our key contribution is that we show that the concept definition can be significantly improved by specifying some negative examples in the input, along with the positive examples. The state-of-the art centroid-based approach to set-expansion doesn't readily admit the negative examples. We develop an inference-based approach to set-expansion which naturally allows for negative examples and show that it performs significantly better than a strong baseline.

AB - This paper addresses the task of set-expansion on free text. Set-expansion has been viewed as a problem of generating an extensive list of instances of a concept of interest, given a few examples of the concept as input. Our key contribution is that we show that the concept definition can be significantly improved by specifying some negative examples in the input, along with the positive examples. The state-of-the art centroid-based approach to set-expansion doesn't readily admit the negative examples. We develop an inference-based approach to set-expansion which naturally allows for negative examples and show that it performs significantly better than a strong baseline.

UR - http://www.scopus.com/inward/record.url?scp=84857174697&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857174697&partnerID=8YFLogxK

U2 - 10.1109/ICDM.2011.86

DO - 10.1109/ICDM.2011.86

M3 - Conference contribution

AN - SCOPUS:84857174697

SN - 9780769544083

T3 - Proceedings - IEEE International Conference on Data Mining, ICDM

SP - 1110

EP - 1115

BT - Proceedings - 11th IEEE International Conference on Data Mining, ICDM 2011

T2 - 11th IEEE International Conference on Data Mining, ICDM 2011

Y2 - 11 December 2011 through 14 December 2011

ER -

Learning from negative examples in set-expansion

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this