Article

Modeling relations and their mentions without labeled text

Authors:

Sebastian Riedel,

Andrew McCallumAuthors Info & Claims

ECML PKDD'10: Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part III

Pages 148 - 163

Published: 20 September 2010 Publication History

Abstract

Several recent works on relation extraction have been applying the distant supervision paradigm: instead of relying on annotated text to learn how to predict relations, they employ existing knowledge bases (KBs) as source of supervision. Crucially, these approaches are trained based on the assumption that each sentence which mentions the two related entities is an expression of the given relation. Here we argue that this leads to noisy patterns that hurt precision, in particular if the knowledge base is not directly related to the text we are working with. We present a novel approach to distant supervision that can alleviate this problem based on the following two ideas: First, we use a factor graph to explicitly model the decision whether two entities are related, and the decision whether this relation is mentioned in a given sentence; second, we apply constraint-driven semi-supervision to train this model without any knowledge about which sentences express the relations in our training KB. We apply our approach to extract relations from the New York Times corpus and use Freebase as knowledge base. When compared to a state-of-the-art approach for relation extraction under distant supervision, we achieve 31% error reduction.

References

[1]

Bellare, K., McCallum, A.: Generalized expectation criteria for bootstrapping extractors using record-text alignment. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 131-140 (2009).

Digital Library

[2]

Bollacker, K., Evans, C., Paritosh, P., Sturge, T., Taylor, J.: Freebase: a collaboratively created graph database for structuring human knowledge. In: SIGMOD '08: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, pp. 1247-1250. ACM, New York (2008).

Digital Library

[3]

Bunescu, R.C., Mooney, R.J.: Learning to extract relations from the web using minimal supervision. In: Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, ACL' 07 (2007).

[4]

Chang, M.W., Goldwasser, D., Roth, D., Tu, Y.: Unsupervised constraint driven learning for transliteration discovery. In: NAACL '09: Proceedings of Human Language Technologies: Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 299-307 (2009).

Digital Library

[5]

Chang, M.W., Ratinov, L., Rizzolo, N., Roth, D.: Learning and inference with constraints. In: AAAI Conference on Artificial Intelligence, pp. 1513-1518. AAAI Press, Menlo Park (2008).

Digital Library

[6]

Chang, M.W., Ratinov, L., Roth, D.: Guiding semi-supervision with constraint-driven learning. In: Annual Meeting of the Association for Computational Linguistics (ACL), pp. 280-287 (2007).

[7]

Collins, M.: Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP '02), vol. 10, pp. 1-8 (2002).

Digital Library

[8]

Craven, M., Kumlien, J.: Constructing biological knowledge-bases by extracting information from text sources. In: Proceedings of the Seventh International Conference on Intelligent Systems for Molecular Biology, Germany, pp. 77-86 (1999).

Digital Library

[9]

Culotta, A., McCallum, A.: Joint deduplication of multiple record types in relational data. In: Proceedings of the 14th ACM International Conference on Information and Knowledge Management (CIKM '05), pp. 257-258. ACM, New York (2005).

Digital Library

[10]

Dietterich, T., Lathrop, R., Lozano-Pérez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artificial Intelligence 89(1-2), 31-71 (1997).

Digital Library

[11]

Dimitry Zelenko, C.A., Richardella, A.: Kernel methods for relation extraction. JMLR 3(6), 1083-1106 (2003).

Digital Library

[12]

Finkel, J.R., Grenager, T., Manning, C.: Incorporating non-local information into information extraction systems by gibbs sampling. In: Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL' 05), pp. 363-370 (June 2005).

Digital Library

[13]

Geman, S., Geman, D.: Stochastic relaxation, gibbs distributions, and the bayesian restoration of images, pp. 452-472 (1990).

Digital Library

[14]

Jensen, C.S., Kong, A., Kjaerulff, U.: Blocking gibbs sampling in very large probabilistic expert systems. International Journal of Human Computer Studies. Special Issue on Real-World Applications of Uncertain Reasoning 42, 647-666 (1993).

Digital Library

[15]

Lafferty, J.D., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: International Conference on Machine Learning, ICML (2001).

Digital Library

[16]

Mann, G.S., McCallum, A.: Generalized expectation criteria for semi-supervised learning of conditional random fields. In: Annual Meeting of the Association for Computational Linguistics (ACL), pp. 870-878 (2008).

[17]

McCallum, A., Schultz, K., Singh, S.: Factorie: Probabilistic programming via imperatively defined factor graphs. In: Bengio, Y., Schuurmans, D., Lafferty, J., Williams, C.K.I., Culotta, A. (eds.) Advances in Neural Information Processing Systems, vol. 22, pp. 1249-1257 (2009).

Digital Library

[18]

Mintz, M., Bills, S., Snow, R., Jurafsky, D.: Distant supervision for relation extraction without labeled data. In: Proceedings of the 47rd Annual Meeting of the Association for Computational Linguistics (ACL' 09), pp. 1003-1011. Association for Computational Linguistics (2009).

Digital Library

[19]

Morgan, A.A., Hirschman, L., Colosimo, M., Yeh, A.S., Colombe, J.B.: Gene name identification and normalization using a model organism database. J. of Biomedical Informatics 37(6), 396-410 (2004).

Digital Library

[20]

Nivre, J., Hall, J., Nilsson, J.: Memory-based dependency parsing. In: Proceedings of CoNLL, pp. 49-56 (2004).

[21]

Rohanimanesh, K., Wick, M., McCallum, A.: Inference and learning in large factor graphs with a rank based objective. Tech. Rep. UM-CS-2009-08, University of Massachusetts, Amherst (2009).

[22]

Sandhaus, E.: The New York Times Annotated Corpus. Linguistic Data Consortium, Philadelphia (2008).

[23]

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

Digital Library

[24]

Singh, S., Yao, L., Riedel, S., McCallum, A.: Constraint-driven rank-based learning for information extraction. In: North American Chapter of the Association for Computational Linguistics - Human Language Technologies, NAACL HLT (2010).

Digital Library

[25]

Smith, N.A., Eisner, J.: Contrastive estimation: training log-linear models on unlabeled data. In: ACL '05: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pp. 354-362. Association for Computational Linguistics, Morristown (2005).

Digital Library

[26]

Sun, X., Matsuzaki, T., Okanohara, D., Tsujii, J.: Latent variable perceptron algorithm for structured classification. In: IJCAI'09: Proceedings of the 21st International Joint Conference on Artifical Intelligence, pp. 1236-1242. Morgan Kaufmann Publishers Inc., San Francisco (2009).

Digital Library

[27]

Wick, M., Rohanimanesh, K., Culotta, A., McCallum, A.: Samplerank: Learning preferences from atomic gradients. In: Neural Information Processing Systems (NIPS), Workshop on Advances in Ranking (2009).

[28]

Wu, F., Weld, D.S.: Autonomously semantifying wikipedia. In: Proceedings of the 16th ACM International Conference on Information and Knowledge Management (CIKM '07), pp. 41-50. ACM Press, New York (2007).

Digital Library

Cited By

Li MGuo LWang L(2023)RSAA: Relation-Specific Attention and Global Alignment Based Joint Entity and Relation ExtractionProceedings of the 2023 4th International Conference on Control, Robotics and Intelligent System10.1145/3622896.3622905(53-58)Online publication date: 25-Aug-2023
https://dl.acm.org/doi/10.1145/3622896.3622905
Li TWang Z(2023)LDRC: Long-tail Distantly Supervised Relation Extraction via Contrastive LearningProceedings of the 2023 7th International Conference on Machine Learning and Soft Computing10.1145/3583788.3583804(110-117)Online publication date: 5-Jan-2023
https://dl.acm.org/doi/10.1145/3583788.3583804
Ghosh MGanguly DBasuchowdhuri PNaskar SFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)Extracting Methodology Components from AI Research Papers: A Data-driven Factored Sequence Labeling ApproachProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3615258(3897-3901)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3615258
Show More Cited By

Index Terms

Modeling relations and their mentions without labeled text
1. Hardware
  1. Power and energy
    1. Power estimation and optimization
      1. Platform power issues

Index terms have been assigned to the content through auto-classification.

Recommendations

Modeling relations and their mentions without labeled text
ECML PKDD'10: Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part III

Several recent works on relation extraction have been applying the distant supervision paradigm: instead of relying on annotated text to learn how to predict relations, they employ existing knowledge bases (KBs) as source of supervision. Crucially, ...
Modeling relations and their mentions without labeled text
ECMLPKDD'10: Proceedings of the 2010th European Conference on Machine Learning and Knowledge Discovery in Databases - Volume Part III

Several recent works on relation extraction have been applying the distant supervision paradigm: instead of relying on annotated text to learn how to predict relations, they employ existing knowledge bases (KBs) as source of supervision. Crucially, ...
Distant supervision for relation extraction without labeled data
ACL '09: Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2

Modern models of relation extraction for tasks like ACE are based on supervised learning of relations from small hand-labeled corpora. We investigate an alternative paradigm that does not require labeled corpora, avoiding the domain dependence of ACE-...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

ECML PKDD'10: Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part III

September 2010

631 pages

ISBN:3642159389

Editors:
José Luis Balcázar
Universidad de Cantabria, Departamento de Matemáticas, Estadística y Computación, Santander, Spain
,
Francesco Bonchi
Yahoo! Research Barcelona, Barcelona, Spain
,
Aristides Gionis
Yahoo! Research Barcelona, Barcelona, Spain
,
Michèle Sebag
TAO, CNRS-INRIA-LRI, Université Paris-Sud, Orsay, France

Sponsors

PASCAL2 - Pattern Analysis, Statistical Modelling and Computational Learning
Google Inc.
Nokia
Yahoo! Research Labs
INRIA: Institut Natl de Recherche en Info et en Automatique

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 20 September 2010

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

75
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 30 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

Li MGuo LWang L(2023)RSAA: Relation-Specific Attention and Global Alignment Based Joint Entity and Relation ExtractionProceedings of the 2023 4th International Conference on Control, Robotics and Intelligent System10.1145/3622896.3622905(53-58)Online publication date: 25-Aug-2023
https://dl.acm.org/doi/10.1145/3622896.3622905
Li TWang Z(2023)LDRC: Long-tail Distantly Supervised Relation Extraction via Contrastive LearningProceedings of the 2023 7th International Conference on Machine Learning and Soft Computing10.1145/3583788.3583804(110-117)Online publication date: 5-Jan-2023
https://dl.acm.org/doi/10.1145/3583788.3583804
Ghosh MGanguly DBasuchowdhuri PNaskar SFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)Extracting Methodology Components from AI Research Papers: A Data-driven Factored Sequence Labeling ApproachProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3615258(3897-3901)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3615258
Strobl MTrabelsi AZaiane OHong JLanperne MPark JCerny TShahriar H(2023)FREDA: Flexible Relation Extraction Data AnnotationProceedings of the 38th ACM/SIGAPP Symposium on Applied Computing10.1145/3555776.3578592(902-910)Online publication date: 27-Mar-2023
https://dl.acm.org/doi/10.1145/3555776.3578592
Yue ZLiu JZhang CWang CJiang HZhang YTian XCen ZXiao YRuan TChen HDuh WHuang HKato MMothe JPoblete B(2023)MA-MRC: A Multi-answer Machine Reading Comprehension DatasetProceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3539618.3592015(2144-2148)Online publication date: 19-Jul-2023
https://dl.acm.org/doi/10.1145/3539618.3592015
Song YMo JPan Z(2022)Online Review System Using Relational Triple Extraction with Novel Data Augmentation MethodsProceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence10.1145/3579654.3579741(1-5)Online publication date: 23-Dec-2022
https://dl.acm.org/doi/10.1145/3579654.3579741
Li RYang CLi TSu S(2022)MiDTD: A Simple and Effective Distillation Framework for Distantly Supervised Relation ExtractionACM Transactions on Information Systems10.1145/350391740:4(1-32)Online publication date: 11-Jan-2022
https://dl.acm.org/doi/10.1145/3503917
Yuan CHuang HFeng C(2021)Multi-Graph Cooperative Learning Towards Distant Supervised Relation ExtractionACM Transactions on Intelligent Systems and Technology10.1145/346656012:5(1-21)Online publication date: 23-Sep-2021
https://dl.acm.org/doi/10.1145/3466560
Gong JEldardiry HDemartini GZuccon GCulpepper JHuang ZTong H(2021)Zero-shot Relation Classification from Side InformationProceedings of the 30th ACM International Conference on Information & Knowledge Management10.1145/3459637.3482403(576-585)Online publication date: 26-Oct-2021
https://dl.acm.org/doi/10.1145/3459637.3482403
Ren FZhang LYin SZhao XLiu SLi BDemartini GZuccon GCulpepper JHuang ZTong H(2021)A Conditional Cascade Model for Relational Triple ExtractionProceedings of the 30th ACM International Conference on Information & Knowledge Management10.1145/3459637.3482045(3393-3397)Online publication date: 26-Oct-2021
https://dl.acm.org/doi/10.1145/3459637.3482045
Show More Cited By

View Options

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

Media

Figures

Other

Tables

View Table of Contents