Spanish Resource Grammar

The Spanish Resource Grammar (SRG) is an open-source multi-purpose large-coverage precise grammar for Spanish. It is grounded in the theoretical framework of Head-driven Phrase Structure Grammar (HPSG) and uses Minimal Recursion Semantics for the semantic representation (Copestake at al., 2005). The SRG is implemented within the Linguistic Knowledge Builder (LKB) system, based on the basic components of the LinGO Grammar Matrix.

To increase the grammar robustness, we have integrated as a pre-processing module FreeLing, an open-source language tool suite performing shallow processing functionalities, ranging from text tokenization to shallow parsing. FreeLing has integrated our morphological dictionary, enlarging its dictionary from 6,500 to 76,000 lemmas. This dictionary can be downloaded from here under the LGPL-LR license.

We are also investigating Machine Learning methods applied to the acquisition of the information contained in the lexicon of the SRG, in the framework of the projects AAILE (HUM2004-0511-C02-01/FILO) and AAILE-2 (HUM2007-61067/FILO), leaded by Núria Bel. See AAILE web page.

The SRG is been developed by Montserrat Marimon at the Institut Universitari de Lingüística Aplicada (IULA) of the Universitat Pompeu Fabra (UPF) and it is funded by the Juan de la Cierva program (MEC, Spain) within the TEXTERM-2 project (BFF2003-2111). The SRG is part of the DELPH-IN open-source repository of linguistic resources and tools for writing, testing and benchmarking, and efficiently processing HPSG grammars.

References

• Montserrat Marimon, Núria Bel, Sergio Espeja and Natalia Seghezzi. The Spanish Resource Grammar: pre-processing strategy and lexical acquisition, in T. Baldwin et al. (eds.) Proceedings of the Workshop on Deep Linguistic Processing, Association for Computational Linguistics (ACL-DLP-2007). [download]

• Montserrat Marimon, Núria Bel and Natalia Seghezzi. Test Suite Construction for a Spanish Grammar, in Tracy Holloway King and Emily M. Bender (eds.) Proceedings of the Grammar Engineering Across Frameworks (GEAF-2007) Workshop "CSLI Studies in Computational Linguistics ONLINE", pp. 250-264. ISSN 1557-5772. [download]

• Montserrat Marimon, Natalia Seghezzi and Núria Bel. An Open-source Lexicon for Spanish, Procesamiento del Lenguaje Natural, n. 39, pp. 131-137. Septiembre, 2007. ISSN 1135-5948. [download]

Download

To download the grammar, under the LGPL-LR license, do the following:

• svn co http://svn.emmtee.net/tags/topp logon
• download the SRG and uncompress the file under the home/logon directory.