A Method of Recognizing Entity and Relation
The entity and relation recognition, i.e. (1) assigning semantic classes to entities in a sentence, and (2) determining the relations held between entities, is an important task in areas such as information extraction. Subtasks (1) and (2) are typically carried out sequentially, but this approach is problematic: the errors made in subtask (1) are propagated to subtask (2) with an accumulative effect; and, the information available only in subtask (2) cannot be used in subtask (1). To address this problem, we propose a method that allows subtasks (1) and (2) to be associated more closely with each other. The process is performed in three stages: firstly, employing two classifiers to do subtasks (1) and (2) independently; secondly, recognizing an entity by taking all the entities and relations into account, using a model called the Entity Relation Propagation Diagram; thirdly, recognizing a relation based on the results of the preceding stage. The experiments show that the proposed method can improve the entity and relation recognition in some degree.
KeywordsEvent Variable Information Extraction Basic Event Question Answering Conditional Probability Distribution
Unable to display preview. Download preview PDF.
- 1.Chinchor, N.: MUC-7 Information Extraction Task Definition. In: Proceeding of the Seventh Message Understanding Conference (MUC-7), Appendices (1998)Google Scholar
- 2.Califf, M., Mooney, R.: Relational Learning of Pattern-match Rules for Information Extraction. In: Proceedings of the Sixteenth National Conference on Artificial Intelligence and Eleventh Conference on Innovative Applications of Artificial Intelligence, Orlando, Florida, USA, pp. 328–334. AAAI Press, Menlo Park (1999)Google Scholar
- 4.Roth, D., Yih, W.: Relational Learning via Prepositional Algorithms: An Information Extraction Case Study. In: Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence, Seattle, Washington, USA, pp. 1257–1263. Morgan Kaufmann, San Francisco (2001)Google Scholar
- 5.Voorhees, E.: Overview of the Trec-9 Question Answering Track. In: The Ninth Text Re-trieval Conference (TREC-9), pp. 71–80 (2000)Google Scholar
- 6.Hirschman, L., Light, M., Breck, E., Burger, J.: Deep Read: A Reading Comprehension System. In: Proceedings of the 37th Annual Meeting of Association for Computational Linguistics (1999)Google Scholar
- 7.Abney, S.P.: Parsing by Chunks. In: Abney, S.P., Berwick, R.C., Tenny, C. (eds.) Principle-based parsing: Computation and Psycholinguistics, pp. 257–278. Kluwer, Dordrecht (1991)Google Scholar
- 8.Fan, X.: Causality Diagram Theory Research and Applying it to Fault Diagnosis of Complexity System, Ph.D. Dissertation of Chongqing University, P.R. China (2002)Google Scholar
- 10.Murphy, K., Weiss, Y., Jordan, M.: Loopy Belief Propagation for Approximate Inference: An empirical study. In: Proceeding of Uncertainty in AI, pp. 467–475 (1999)Google Scholar
- 11.Roth, D., Yih, W.: Probability Reasoning for Entity & Relation Recognition. In: Proceedings of 20th International Conference on Computational Linguistics (COLING-2002), pp. 835–841 (2002)Google Scholar
- 12.Pearl, J.: Probability Reasoning in Intelligence Systems. Morgan Kaufmann, San Francisco (1988)Google Scholar