Learning-based multi-sieve co-reference resolution with knowledge

Lev Ratinov; Dan Roth

Learning-based multi-sieve co-reference resolution with knowledge

Lev Ratinov
, Dan Roth

Siebel School of Computing and Data Science

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

Abstract

We explore the interplay of knowledge and structure in co-reference resolution. To inject knowledge, we use a state-of-the-art system which cross-links (or "grounds") expressions in free text to Wikipedia. We explore ways of using the resulting grounding to boost the performance of a state-of-the-art co-reference resolution system. To maximize the utility of the injected knowledge, we deploy a learning-based multi-sieve approach and develop novel entity-based features. Our end system outperforms the state-of-the-art baseline by 2 B³ F1 points on non-transcript portion of the ACE 2004 dataset.

Original language	English (US)
Title of host publication	EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference
Pages	1234-1244
Number of pages	11
State	Published - 2012
Event	2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012 - Jeju Island, Korea, Republic of Duration: Jul 12 2012 → Jul 14 2012

Publication series

Name	EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference

Other

Other	2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012
Country/Territory	Korea, Republic of
City	Jeju Island
Period	7/12/12 → 7/14/12

ASJC Scopus subject areas

Software

Library availability

Discover UIUC Full Text

Cite this

Ratinov, L., & Roth, D. (2012). Learning-based multi-sieve co-reference resolution with knowledge. In EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference (pp. 1234-1244). (EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference).

Learning-based multi-sieve co-reference resolution with knowledge. / Ratinov, Lev; Roth, Dan.
EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference. 2012. p. 1234-1244 (EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference).

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

Ratinov, L & Roth, D 2012, Learning-based multi-sieve co-reference resolution with knowledge. in EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference. EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference, pp. 1234-1244, 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012, Jeju Island, Korea, Republic of, 7/12/12.

Ratinov L, Roth D. Learning-based multi-sieve co-reference resolution with knowledge. In EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference. 2012. p. 1234-1244. (EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference).

Ratinov, Lev ; Roth, Dan. / Learning-based multi-sieve co-reference resolution with knowledge. EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference. 2012. pp. 1234-1244 (EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference).

@inproceedings{9648552dea7845b0bf259c49c6522f18,

title = "Learning-based multi-sieve co-reference resolution with knowledge",

abstract = "We explore the interplay of knowledge and structure in co-reference resolution. To inject knowledge, we use a state-of-the-art system which cross-links (or {"}grounds{"}) expressions in free text to Wikipedia. We explore ways of using the resulting grounding to boost the performance of a state-of-the-art co-reference resolution system. To maximize the utility of the injected knowledge, we deploy a learning-based multi-sieve approach and develop novel entity-based features. Our end system outperforms the state-of-the-art baseline by 2 B3 F1 points on non-transcript portion of the ACE 2004 dataset.",

author = "Lev Ratinov and Dan Roth",

year = "2012",

language = "English (US)",

isbn = "9781937284435",

series = "EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference",

pages = "1234--1244",

booktitle = "EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference",

note = "2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012 ; Conference date: 12-07-2012 Through 14-07-2012",

}

TY - GEN

T1 - Learning-based multi-sieve co-reference resolution with knowledge

AU - Ratinov, Lev

AU - Roth, Dan

PY - 2012

Y1 - 2012

N2 - We explore the interplay of knowledge and structure in co-reference resolution. To inject knowledge, we use a state-of-the-art system which cross-links (or "grounds") expressions in free text to Wikipedia. We explore ways of using the resulting grounding to boost the performance of a state-of-the-art co-reference resolution system. To maximize the utility of the injected knowledge, we deploy a learning-based multi-sieve approach and develop novel entity-based features. Our end system outperforms the state-of-the-art baseline by 2 B3 F1 points on non-transcript portion of the ACE 2004 dataset.

AB - We explore the interplay of knowledge and structure in co-reference resolution. To inject knowledge, we use a state-of-the-art system which cross-links (or "grounds") expressions in free text to Wikipedia. We explore ways of using the resulting grounding to boost the performance of a state-of-the-art co-reference resolution system. To maximize the utility of the injected knowledge, we deploy a learning-based multi-sieve approach and develop novel entity-based features. Our end system outperforms the state-of-the-art baseline by 2 B3 F1 points on non-transcript portion of the ACE 2004 dataset.

UR - https://www.scopus.com/pages/publications/84883368040

UR - https://www.scopus.com/pages/publications/84883368040#tab=citedBy

M3 - Conference contribution

AN - SCOPUS:84883368040

SN - 9781937284435

T3 - EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference

SP - 1234

EP - 1244

BT - EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference

T2 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012

Y2 - 12 July 2012 through 14 July 2012

ER -

Learning-based multi-sieve co-reference resolution with knowledge

Abstract

Publication series

Other

ASJC Scopus subject areas

Library availability

Related links

Fingerprint

Cite this