Resolving Relative Time Expressions in Dutch Text with Constraint Handling Rules

It is demonstrated how Constraint Handling Rules can be applied for resolution of indirect and relative time expressions in text as part of a shallow analysis, following a specialized tagging phase. A method is currently under development, optimized for a particular corpus of historical biographies related to the development of the Dutch social movement between 1870 and 1940. It appears that CHR provides a modular language which is well-suited for tailoring a method optimized for the different linguistic constructs and the textual conventions applied in a specific corpus. We explain the principles and illustrate by sample rules. The project is currently in a phase of development and testing, and this paper focuses on the methodological issues, while a detailed evaluation is not relevant at present. Identified problems and possible extensions are discussed.

[1]  Patrick Brézillon,et al.  Modeling and Using Context , 1999, Lecture Notes in Computer Science.

[2]  V. Dahl,et al.  A CHRG Analysis of ambiguity in Biological Texts , 2007 .

[3]  Walter Daelemans,et al.  An efficient memory-based morphosyntactic tagger and parser for Dutch , 2007, CLIN 2007.

[4]  António Branco,et al.  Extracting Temporal Information from Portuguese Texts , 2012, PROPOR.

[5]  Henning Christiansen,et al.  From use cases to UML class diagrams using logic grammars and constraints , 2007 .

[6]  Francesca Rossi,et al.  Soft Constraint Propagation and Solving in Constraint Handling Rules , 2004, Comput. Intell..

[7]  Verónica Dahl,et al.  Implantation de grammaires de propriétés en CHR , 2004, JFPLC.

[8]  Thiago Alexandre Salgueiro Pardo,et al.  Computational Processing of the Portuguese Language - 11th International Conference, PROPOR 2014, São Carlos/SP, Brazil, October 6-8, 2014. Proceedings , 2014, Lecture Notes in Computer Science.

[9]  Henning Christiansen,et al.  Reasoning about Use Cases using Logic Grammars and Constraints , 2007 .

[10]  Verónica Dahl,et al.  Meaning in Context , 2005, CONTEXT.

[11]  Michael Gertz,et al.  HeidelTime: High Quality Rule-Based Extraction and Normalization of Temporal Expressions , 2010, *SEMEVAL.

[12]  James Pustejovsky,et al.  The TempEval challenge: identifying temporal relations in text , 2009, Lang. Resour. Evaluation.

[13]  Verónica Dahl,et al.  Constraint Based Methods for Biological Sequence Analysis , 2006, J. Univers. Comput. Sci..

[14]  Thom W. Frühwirth,et al.  Constraint Handling Rules , 2009, Constraint Programming.

[15]  Wannes Meert,et al.  CHR(PRISM)-based probabilistic logic learning , 2010, Theory Pract. Log. Program..

[16]  Siddharth Patwardhan,et al.  When Did that Happen? - Linking Events and Relations to Timestamps , 2012, EACL.

[17]  Thom W. Frühwirth,et al.  Theory and Practice of Constraint Handling Rules , 1998, J. Log. Program..

[18]  Christopher D. Manning,et al.  Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling , 2005, ACL.

[19]  Gerald Penn,et al.  The Other Syntax: Approaching Natural Language Semantics Through Logical Form Composition , 2004, CSLP.

[20]  Michael Gertz,et al.  Multilingual and cross-domain temporal tagging , 2012, Language Resources and Evaluation.

[21]  Henning Christiansen,et al.  CHR grammars , 2004, Theory and Practice of Logic Programming.

[22]  Henning Christiansen,et al.  Approaching the Chinese Word Segmentation Problem with CHR Grammars , 2011 .