In this demo we present the first version of Txala, a dependency parser for Spanish developed under LGPL license. This parser is framed in the development of a free-software platform for Machine Translation. Due to the lack of this kind of syntactic parsers for Spanish, this tool is essential for the development of NLP in Spanish.
We are working on the construction of a Spanish-Basque (es-eu) machine translation tool using the traditional transfer model based on shallow and dependency parsing. Spanish and Basque languages are very different and one of the main problems is the translation of the verb chain. We will present the features of each language verb chain, and the design of… (More)
We present some Language Technology applications that have proven to be effec tive tools to promote use of Basque, a low density language. We also present the strat egy we have followed for almost twenty years to develop those applications as the top of an integrated environment of lan guage resources, language foundations, language tools and other… (More)
This paper presents the strategy and design of a highly efficient semiautomatic method for labelling the semantic features of common nouns, using semantic relationships between words, and based on the information extracted from an electronic monolingual dictionary. The method, that uses genus data, specific relators and synonymy information, obtains an… (More)
Matxin is a rule-based machine translation system which translates to Basque. For its evaluation we have used the HTER metric which calculates the post-editing cost, concluding that 4 of each 10 words would have to be modified to correct the output generated by the system. We have compared the quality of Matxin translations with that of a corpus based… (More)
We present the first steps in the definition of a mixing approach to MT for Basque based on combining single engines that follow to three different MT paradigms. After describing each engine we present the hierarchical strategy we use in order to select the best output, and a first evaluation.
This paper presents the current status of development of a finite state transducer grammar for the verbal-chain transfer module in Matxin, a Rule Based Machine Translation system between Spanish and Basque. Due to the distance between Spanish and Basque, the verbal-chain transfer is a very complex module in the overall system. The grammar is compiled with… (More)
Adaptación del léxico al dominio Desarrollo de un corpus de postedición para su uso en postedición estadística Recopilación de corpus paralelo ● Del dominio de la informática ● Creado en la localización de Sw Tratamiento del corpus ● Analizado, lematizado y procesado con Giza++ ● Para cada lema (es) se extraen: ● sus posibles traducciones (eu) ● y su… (More)