Proceedings

Predicting Globally-Coherent Temporal Structures from Texts via Endpoint Inference and Graph Decomposition

Download BibTeX Cite

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 1788-1792.

https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-300

© 2011 International Joint Conferences on Artificial Intelligence

Abstract

An elegant approach to learning temporal orderings from texts is to formulate this problem as a constraint optimization problem, which can be then given an exact solution using Integer Linear Programming. This works well for cases where the number of possible relations between temporal entities is restricted to the mere precedence relation [Bramsen et al., 2006; Chambers and Jurafsky, 2008], but becomes impractical when considering all possible interval relations. This paper proposes two innovations, inspired from work on temporal reasoning, that control this combinatorial blow-up, therefore rendering an exact ILP inference viable in the general case. First, we translate our network of constraints from temporal intervals to their endpoints, to handle a drastically smaller set of constraints, while preserving the same temporal information. Second, we show that additional efficiency is gained by enforcing coherence on particular subsets of the entire temporal graphs. We evaluate these innovations through various experiments on TimeBank 1.2, and compare our ILP formulations with various baselines and oracle systems.

  1. [Allen, 1983] J. Allen. Maintaining knowledge about tem- poral intervals. Communications of the ACM, 1983.
  2. [Bethard et al., 2007] S. Bethard, J. H. Martin, and S. Klin- genstein. Timelines from text: Identification of syntactic temporal relations. In Proc. of ICSC, 2007.
  3. [Bramsen et al., 2006] P. Bramsen, P. Deshpande, Y. K. Lee, and R. Barzilay. Inducing temporal graphs. In Proc. of EMNLP, 2006.
  4. [Chambers and Jurafsky, 2008] N. Chambers and D. Juraf- sky. Jointly combining implicit constraints improves tem- poral ordering. In Proc. of EMNLP, 2008.
  5. [Mani et al., 2006] I. Mani, M. Verhagen, B. Wellner, C. M. Lee, and J. Pustejovsky. Machine learning of temporal relations. In Proc. of ACL, 2006.
  6. [Pustejovsky et al., 2005] J. Pustejovsky, R. Ingria, R. Sauri, J. Castano, J. Littman, R. Gaizauskas, A. Setzer, G. Katz, and I. Mani. The specification language TimeML. In I. Mani, J. Pustejovsky, and R Gaizauskas, editors, The Language of Time: A Reader. OUP, 2005.
  7. [Tatu and Srikanth, 2008] M. Tatu and M. Srikanth. Ex- periments with reasoning for temporal relations between events. In Proc. of Coling, 2008.
  8. [Van Beek, 1990] P. Van Beek. Exact and approximate rea- soning about qualitative temporal relations. PhD thesis, University of Waterloo, Canada, 1990.
  9. [Verhagen et al., 2010] M. Verhagen, R. Sauri, T. Caselli, and J. Pustejovsky. Semeval-2010 task 13: Tempeval-2. In Proc. of the 5th International Workshop on Semantic Evaluation, 2010.
  10. [Verhagen, 2005] M. Verhagen. Temporal closure in an an- notation environment. Language Resources and Evalua- tion, 39(2), 2005.
  11. [Vilain et al., 1990] M. Vilain, H. Kautz, and P. van Beek. Constraint propagation algorithms for temporal reasoning: a revised report. 1990.
  12. [Yoshikawa et al., 2009] K. Yoshikawa, S. Riedel, M. Asa- hara, and Y. Matsumoto. Jointly identifying temporal re- lations with markov logic. In Proc. of ACL, 2009.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards