research-article

Joint inference of entities, relations, and coreference

Authors:

Sebastian Riedel,

Andrew McCallumAuthors Info & Claims

AKBC '13: Proceedings of the 2013 workshop on Automated knowledge base construction

Pages 1 - 6

https://doi.org/10.1145/2509558.2509559

Published: 27 October 2013 Publication History

Abstract

Although joint inference is an effective approach to avoid cascading of errors when inferring multiple natural language tasks, its application to information extraction has been limited to modeling only two tasks at a time, leading to modest improvements. In this paper, we focus on the three crucial tasks of automated extraction pipelines: entity tagging, relation extraction, and coreference. We propose a single, joint graphical model that represents the various dependencies between the tasks, allowing flow of uncertainty across task boundaries. Since the resulting model has a high tree-width and contains a large number of variables, we present a novel extension to belief propagation that sparsifies the domains of variables during inference. Experimental results show that our joint model consistently improves results on all three tasks as we represent more dependencies. In particular, our joint model obtains 12% error reduction on tagging over the isolated models.

References

[1]

O. Bender, F. Och, and H. Ney. Maximum entropy models for named entity recognition. In phNorth American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT), pages 148--151. Association for Computational Linguistics, 2003.

Digital Library

[2]

E. Bengston and D. Roth. Understanding the value of features for coreference resolution. In phEmpirical Methods in Natural Language Processing (EMNLP), 2008.

Digital Library

[3]

A. Culotta, M. Wick, and A. McCallum. First-order probabilistic models for coreference resolution. In phNorth American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT), 2007.

[4]

G. Doddington, A. Mitchell, M. Przybocki, L. Ramshaw, S. Strassel, and R. Weischedel. The Automatic Content Extraction (ACE) program--tasks, data, and evaluation. In phProceedings of LREC, volume 4, pages 837--840. Citeseer, 2004.

[5]

J. R. Finkel and C. D. Manning. Joint parsing and named entity recognition. In phNorth American Chapter of the Association for Computational Linguistics (NAACL HLT), 2009.

Digital Library

[6]

J. R. Finkel, C. D. Manning, and A. Y. Ng. Solving the problem of cascading errors: Approximate bayesian inference for linguistic annotation pipelines. In phEmpirical Methods in Natural Language Processing (EMNLP), 2006.

Digital Library

[7]

A. Haghighi and D. Klein. Simple coreference resolution with rich syntactic and semantic features. In phEmpirical Methods in Natural Language Processing (EMNLP), pages 1152--1161, 2009.

Digital Library

[8]

A. Haghighi and D. Klein. Coreference resolution in a modular, entity-centered model. In phNorth American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT), pages 385--393, 2010.

Digital Library

[9]

J. Jiang and C. Zhai. A systematic exploration of the feature space for relation extraction. In phNorth American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT), pages 113--120, Rochester, New York, April 2007. Association for Computational Linguistics.

[10]

R. J. Kate and R. J. Mooney. Joint entity and relation extraction using card-pyramid parsing. In phConference on Computational Natural Language Learning (CoNLL), 2010.

Digital Library

[11]

F. R. Kschischang, B. J. Frey, and H. A. Loeliger. Factor graphs and the sum-product algorithm. phIEEE Transactions of Information Theory, 47 (2): 498--519, Feb 2001.

Digital Library

[12]

A. Kulesza and F. Pereira. Structured learning with approximate inference. In phNeural Information Processing Systems (NIPS), 2008.

[13]

A. McCallum and D. Jensen. A note on the unification of information extraction and data mining using conditional-probability, relational models. In phIJCAI Workshop on Learning Statistical Models from Relational Data, 2003.

[14]

A. McCallum, K. Nigam, J. Rennie, and K. Seymore. A machine learning approach to building domain-specific search engines. In phInternational Joint Conference on Artificial Intelligence (IJCAI), 1999.

Digital Library

[15]

V. Ng and C. Cardie. Improving machine learning approaches to coreference resolution. In phAnnual Meeting of the Association for Computational Linguistics (ACL), pages 104--111, 2002.

Digital Library

[16]

H. Poon and P. Domingos. Joint inference in information extraction. In phAAAI Conference on Artificial Intelligence, pages 913--918, 2007.

Digital Library

[17]

H. Poon and L. Vanderwende. Joint Inference for Knowledge Extraction from Biomedical Literature. In phNorth American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT), pages 813--821, Los Angeles, California, June 2010. Association for Computational Linguistics. URL http://www.aclweb.org/anthology-new/N/N10/N10--1123.bib.

Digital Library

[18]

L. Ratinov and D. Roth. Design challenges and misconceptions in named entity recognition. In phConference on Computational Natural Language Learning (CoNLL), pages 147--155. Association for Computational Linguistics, 2009.

Digital Library

[19]

lum(2011)}riedel11:fastS. Riedel and A. McCallum. Fast and robust joint models for biomedical event extraction. In phEmpirical Methods in Natural Language Processing (EMNLP), 2011.

Digital Library

[20]

D. Roth and W. Yih. Global inference for entity and relation identification via a linear programming formulation. In L. Getoor and B. Taskar, editors, phIntroduction to Statistical Relational Learning. MIT Press, 2007.

[21]

S. Singh, K. Schultz, and A. McCallum. Bi-directional joint inference for entity resolution and segmentation using imperatively-defined factor graphs. In phMachine Learning and Knowledge Discovery in Databases (Lecture Notes in Computer Science) and European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), pages 414--429, 2009.

Digital Library

[22]

lum}singh11:inducingS. Singh, B. Martin, and A. McCallum. Inducing value sparsity for parallel inference in tree-shaped models. In phNeural Information Processing Systems (NIPS), Workshop on Computational Trade-offs in Statistical Learning (COST), 2011.

[23]

W. M. Soon, H. T. Ng, and D. C. Y. Lim. A machine learning approach to coreference resolution of noun phrases. phComputational Linguistics, 27 (4): 521--544, Dec 2001.

Digital Library

[24]

A. Sun, R. Grishman, and S. Sekine. Semi-supervised relation extraction with large-scale word clustering. In phAnnual Meeting of the Association for Computational Linguistics (ACL), pages 521--529, Portland, Oregon, USA, June 2011. Association for Computational Linguistics.

Digital Library

[25]

uez, and Nivre}surdeanu08:the-conll-2008M. Surdeanu, R. Johansson, A. Meyers, L. Màrquez, and J. Nivre. The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies. In phConference on Computational Natural Language Learning (CoNLL), 2008.

Digital Library

[26]

C. Sutton and A. McCallum. Joint parsing and semantic role labeling. In phConference on Computational Natural Language Learning (CoNLL), 2005.

Digital Library

[27]

C. Sutton and A. McCallum. Piecewise training for structured prediction. phMachine Learning, 77 (2--3): 165--194, 2009.

Digital Library

[28]

E. F. Tjong Kim Sang and F. De Meulder. Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. In phNorth American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT), pages 142--147. Association for Computational Linguistics, 2003.

Digital Library

[29]

B. Wellner, A. McCallum, F. Peng, and M. Hay. An integrated, conditional model of information extraction and coreference with application to citation matching. In phUncertainty in Artificial Intelligence (UAI), pages 593--601, 2004.

Digital Library

[30]

C. Yanover, T. Meltzer, and Y. Weiss. Linear programming relaxations and belief propagation -- an empirical study. phJournal of Machine Learning Research (JMLR), 7: 1887--1907, Dec. 2006. ISSN 1532--4435.

Digital Library

[31]

L. Yao, S. Riedel, and A. McCallum. Collective cross-document relation extraction without labelled data. In phEmpirical Methods in Natural Language Processing (EMNLP), 2010.

Digital Library

[32]

X. Yu and W. Lam. Jointly identifying entities and extracting relations in encyclopedia text via a graphical model approach. In phInternational Conference on Computational Linguistics (COLING), pages 1399--1407, Beijing, China, August 2010. Coling 2010 Organizing Committee.

Digital Library

[33]

M. Zhang, J. Zhang, and J. Su. Exploring syntactic features for relation extraction using a convolution tree kernel. In phNorth American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT), HLT-NAACL '06, pages 288--295, Stroudsburg, PA, USA, 2006. Association for Computational Linguistics. 10.3115/1220835.1220872. URL http://dx.doi.org/10.3115/1220835.1220872.

Digital Library

[34]

G. Zhou, J. Su, J. Zhang, and M. Zhang. Exploring various knowledge in relation extraction. In phAnnual Meeting of the Association for Computational Linguistics (ACL), pages 427--434, Ann Arbor, Michigan, June 2005. Association for Computational Linguistics.

Digital Library

[35]

G. Zhou, M. Zhang, D. Ji, and Q. Zhu. Tree kernel-based relation extraction with context-sensitive structured parse tree information. In phEmpirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pages 728--736, 2007.

Cited By

Zhang XYu CYan R(2024)ParTRE: A relational triple extraction model of complicated entities and imbalanced relations in Parkinson’s diseaseJournal of Biomedical Informatics10.1016/j.jbi.2024.104624152(104624)Online publication date: Apr-2024
https://doi.org/10.1016/j.jbi.2024.104624
Ahmad PKhan K(2023)Propaganda Detection And Challenges Managing Smart Cities Information On Social MediaEAI Endorsed Transactions on Smart Cities10.4108/eetsc.v7i2.29257:2(e2)Online publication date: 30-Mar-2023
https://doi.org/10.4108/eetsc.v7i2.2925
Chai YChen MWu HWang S(2023)Fin-EMRC: An Efficient Machine Reading Comprehension Framework for Financial Entity-Relation ExtractionIEEE Access10.1109/ACCESS.2023.329988011(82685-82695)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3299880
Show More Cited By

Index Terms

Joint inference of entities, relations, and coreference
1. Computing methodologies
  1. Artificial intelligence
    1. Natural language processing

Recommendations

A Flexible Text Mining System for Entity and Relation Extraction in PubMed
DTMBIO '15: Proceedings of the ACM Ninth International Workshop on Data and Text Mining in Biomedical Informatics

Due to an enormous number of scientific publications that cannot be handled manually, there is a rising interest in text-mining techniques for automated information extraction, especially in the biomedical field. Such techniques provide effective means ...
Joint inference for end-to-end coreference resolution for clinical notes
BCB '14: Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

Recent US government initiatives have led to wide adoption of Electronic Health Records (EHRs). More and more health care institutions are storing patients' data in an electronic format. These EHRs contain valuable information which can be used in ...
NEREL: a Russian information extraction dataset with rich annotation for nested entities, relations, and wikidata entity links
Abstract
This paper describes NEREL—a Russian news dataset suited for three tasks: nested named entity recognition, relation extraction, and entity linking. Compared to flat entities, nested named entities provide a richer and more complete annotation ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

AKBC '13: Proceedings of the 2013 workshop on Automated knowledge base construction

October 2013

124 pages

ISBN:9781450324113

DOI:10.1145/2509558

Program Chairs:
Fabian M. Suchanek
Max Planck Institute for Informatics, Germany
,
Sebastian Riedel
University College London, UK
,
Sameer Singh
University of Massachusetts Amherst, USA
,
Partha Pratim Talukdar
Carnegie Mellon University, USA

Copyright © 2013 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 27 October 2013

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

CIKM'13

Sponsor:

CIKM'13: 22nd ACM International Conference on Information and Knowledge Management

October 27 - 28, 2013

California, San Francisco, USA

Acceptance Rates

AKBC '13 Paper Acceptance Rate 9 of 19 submissions, 47%;

Overall Acceptance Rate 9 of 19 submissions, 47%

Upcoming Conference

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

44
Total Citations
View Citations
456
Total Downloads

Downloads (Last 12 months)13
Downloads (Last 6 weeks)1

Reflects downloads up to 30 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

Zhang XYu CYan R(2024)ParTRE: A relational triple extraction model of complicated entities and imbalanced relations in Parkinson’s diseaseJournal of Biomedical Informatics10.1016/j.jbi.2024.104624152(104624)Online publication date: Apr-2024
https://doi.org/10.1016/j.jbi.2024.104624
Ahmad PKhan K(2023)Propaganda Detection And Challenges Managing Smart Cities Information On Social MediaEAI Endorsed Transactions on Smart Cities10.4108/eetsc.v7i2.29257:2(e2)Online publication date: 30-Mar-2023
https://doi.org/10.4108/eetsc.v7i2.2925
Chai YChen MWu HWang S(2023)Fin-EMRC: An Efficient Machine Reading Comprehension Framework for Financial Entity-Relation ExtractionIEEE Access10.1109/ACCESS.2023.329988011(82685-82695)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3299880
Liu PQian LZhao XTao B(2023)The Construction of Knowledge Graphs in the Aviation Assembly Domain Based on a Joint Knowledge Extraction ModelIEEE Access10.1109/ACCESS.2023.325413211(26483-26495)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3254132
Liu ZLi HWang HLiao YLiu XWu G(2023)A novel pipelined end-to-end relation extraction framework with entity mentions and contextual semantic representationExpert Systems with Applications: An International Journal10.1016/j.eswa.2023.120435228:COnline publication date: 15-Oct-2023
https://dl.acm.org/doi/10.1016/j.eswa.2023.120435
Ren HYang MJiang P(2023)Improving attention network to realize joint extraction for the construction of equipment knowledge graphEngineering Applications of Artificial Intelligence10.1016/j.engappai.2023.106723125:COnline publication date: 1-Oct-2023
https://dl.acm.org/doi/10.1016/j.engappai.2023.106723
ter Horst HBrazda NSchira-Heinen JKrebbers JMüller HCimiano P(2023)Automatic knowledge graph population with model-complete text comprehension for pre-clinical outcomes in the field of spinal cord injuryArtificial Intelligence in Medicine10.1016/j.artmed.2023.102491137(102491)Online publication date: Mar-2023
https://doi.org/10.1016/j.artmed.2023.102491
Zheng YTuan L(2023)A Novel, Cognitively Inspired, Unified Graph-based Multi-Task Framework for Information ExtractionCognitive Computation10.1007/s12559-023-10163-215:6(2004-2013)Online publication date: 6-Jul-2023
https://doi.org/10.1007/s12559-023-10163-2
Wang RHou FCahan SChen LJia XJi W(2022)Fine-Grained Entity Typing with a Type Taxonomy: a Systematic ReviewIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2022.3148980(1-1)Online publication date: 2022
https://doi.org/10.1109/TKDE.2022.3148980
Zhu PCheng DYang FLuo YHuang DQian WZhou A(2022)Improving Chinese Named Entity Recognition by Large-Scale Syntactic Dependency GraphIEEE/ACM Transactions on Audio, Speech, and Language Processing10.1109/TASLP.2022.315326130(979-991)Online publication date: 2022
https://doi.org/10.1109/TASLP.2022.3153261
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents