Autores: | Hector Llorens, Estela Saquete, Borja Navarro-Colorado |
URL: | http://gplsi.dlsi.ua.es/demos/TIMEE/ |
Contacto: | Hector Llorens <hllorensdlsi.ua.es>, DLSI, Universidad de Alicante |
Descripción
TIPSem is a temporal information processing tool for English and Spanish. This is based on semantics (lexical and compositional), in addition to morphosyntax.
Funcionalidad
Given a raw text, this outputs its TimeML annotation (http://timeml.org). TIPSem performs the following processes:==Technology== C++
- temporal expression recognition, classification and normalization.
- event recognition and classification.
- temporal relation identification and categorization.
Tecnología
The tool is programmed in Java but is currently offered as an online application in the following URL: http://gplsi.dlsi.ua.es/demos/TIMEE/
Requisitos técnicos
A standard web browser and Internet connection.
Módulos
Innovación
TIPSem makes a extensive usage of lexical semantics (WordNet and EuroWordNet) and compositional semantics (semantic roles) to perform the temporal information processing and achieves a competitive performance in comparison with the state-of-art approaches. It is the only available multilingual tool (including a complete temporal information processing in Spanish).
Desarrollo
This was part of the development of a thesis supported by the Spanish Government, projects TIN-2006-15265-C06-01, where Hector Llorens is funded under a FPI grant (BES-2007-16256).
Publicaciones
- Llorens, H., Saquete, E., & Navarro-Colorado, B. (2010b). TIPSem (English and Spanish): Evaluating CRFs and Semantic Roles in TempEval-2. In Proceedings of the 5th International Workshop on Semantic Evaluation, pp. 28491. ACL.
- Llorens, H., Saquete, E., & Navarro-Colorado, B. (2010a). TimeML Events Recognition and Classification: Learning CRF Models with Semantic Roles. In Proceedings of the 23rd International Conference on Com-putational Linguistics (Coling 2010), pp. 72533.