ID 392:TERSEO + T2T3 Transducer. A systems for Recognizing and Normalizing TIMEX3

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 317–320, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics ID 392:TERSEO + T2T3 Transducer. A systems for recognizing and normalizing TIMEX3 Estela Saquete Natural Language Processing and Information System Group University of Alicante stela@dlsi.ua.es Abstract The system described in this paper has par- ticipated in the Tempeval 2 competition, specifically in the Task A, which aim is to determine the extent of the time expres- sions in a text as defined by the TimeML TIMEX3 tag, and the value of the fea- tures type and val. For this purpose, a combination of TERSEO system and the T2T3 Transducer was used. TERSEO sys- tem is able to annotate text with TIDES TIMEX2 tags, and T2T3 transducer per- forms the translation from this TIMEX2 tags to TIMEX3 tags. 1 Introduction Identification and extraction of explicit and im- plicit temporal information has become a very im- portant field of research within the computational linguistics area since some years ago (Allen, 1983) (Allen, 1984). Moreover, a large number of NLP applications are exploiting this extracted informa- tion, such as question answering and summariza- tion systems, allowing these applications to per- form in a more complex level. When dealing with temporal information iden- tification and normalization, different approaches can be taken, depending on the available resources of the target language and the requirements of the system being developed. The most extended ap- proaches to the problem are: a) rule-based ap- proaches, such as Chronos (ITC-irst): recognizes and normalizes temporal expressions in English and Italian (Negri, 2007); TERSEO (University of Alicante, the system used for this work): a knowl- edge based system for Spanish that has been auto- matically extended to other languages, such as En- glish, Italian and Catalan (Saquete et al., 2006), b) machine learning approaches, such as TimexTag (University of Amsterdam): applies data-driven methods for recognition and normalization tasks (Ahn et al., 2005) (Ahn, 2006); CU-TMP (Uni- versity of Colorado): uses machine learning for automatic annotation (Bethard and Martin, 2007), and c) mixed combination of rules and ML ap- proaches, such as, TempEx (MITRE Corpora- tion): combines hand-coded patterns with ma- chine learning rules to tag documents (TempEx, 2008) (Mani and Wilson, 2000); TARSQI (Bran- deis University): currently uses GUTime (2008) for temporal expression annotation, which extends the capabilities of the TempEx tagger while gener- ating TIMEX3 annotations (Verhagen et al., 2005). However, whatever the approach, the output of these systems is a standardized annotation scheme. The most popular annotation schemes are TIDES (Mani et al., 2001) and TimeML (Puste- jovsky et al., 2003b). TIDES program followed the efforts started in the context of the Message Understanding Conference, MUC (1998), and de- fined the TIMEX2 tag, with the goal of interpret- ing temporal expressions within a normalized rep- resentation of the times they denote, adopting the ISO 8601 standard (Technical Committee ISO/TC 154, 2004). In 2004, within the ACE program, the Time Expression Recognition and Normalization (TERN, 2004) evaluation …

Content truncated to 500 words