NCSU: Modeling Temporal Relations with Markov Logic and Lexical Ontology

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 341–344, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics NCSU: Modeling Temporal Relations with Markov Logic and Lexical Ontology Eun Young Ha Alok Baikadi Carlyle Licata James C. Lester Department of Computer Science North Carolina State University Raleigh, NC, USA {eha,abaikad,cjlicata,lester}@ncsu.edu Abstract As a participant in TempEval-2, we ad- dress the temporal relations task consist- ing of four related subtasks. We take a su- pervised machine-learning technique us- ing Markov Logic in combination with rich lexical relations beyond basic and syntactic features. One of our two submit- ted systems achieved the highest score for the Task F (66% precision), untied, and the second highest score (63% precision) for the Task C, which tied with three other systems. 1 Introduction Time plays a key role in narrative. However, cor- rectly recognizing temporal order among events is a challenging task. As a follow-up to the first TempEval competition, TempEval-2 addresses this challenge. Among the three proposed tasks of TempEval-2, we address the temporal rela- tions task consisting of four subtasks: predicting temporal relations that hold between events and time expressions in the same sentence (Task C), events and the document creation time (Task D), main events in adjacent sentences (Task E), and main events and syntactically dominated events, such as those in subordinated clauses (Task F). We are primarily concerned with Task C, E, and F, because D is not relevant to our application domain.1 However, rather than eliminating Task D altogether, we build a very simple model for this task by using only those features that are shared with other task models (i.e., the document 1 Our application domain concerns analysis of narrative stories written by middle school students, with the analysis being conducted a single story at a time. creation time data are not used because none of the other task models need them as features). It was expected that this approach would support more interesting comparisons with other systems that take a more sophisticated approach to the task. Further, we experiment with a joint model- ing technique to examine if the communication with other task models brings a boost to a per- formance of the simple model. Taking a supervised machine-learning ap- proach with Markov Logic (ML) (Richardson and Domingos, 2006), we constructed two systems, NCSU-INDI and NCSU-JOINT. NCSU-INDI con- sists of four independently trained classifiers, one for each task, whereas NCSU-JOINT models all four tasks jointly. The choice of ML as learn- ing technique for temporal relations is motivated both theoretically and practically. Theoretically, it is a statistical relational learning framework that does not make the i.i.d. assumption for the data. This is a desirable characteristic for com- plex problems such as temporal relation classifi- cation, as well as many other natural language problems, in which the features representing a given problem are often correlated with one an- other. Practically, ML allows us to build both individual and joint models in a uniform frame- …

Content truncated to 500 words