![]() ![]() Nowadays, if any patient wants to consult their health record in Basque, it is translated on demand by human translators, the translation is given to the patient, and the public health service does not retain a copy. This is reflected in the Basque public health service, where nearly all of the health records are registered in Spanish so that any doctor can understand them. Specifically, distinct configurations of neural machine translation (NMT) systems were tested leveraging the limited resources available for the clinical domain in Basque and Spanish.īasque is a minoritized language, sharing a bilingual environment with the strong language Spanish. In this sense, XUXEN is intended as a useful tool for standardization purposes of present day written Basque.Our objective is to analyze different techniques for Basque-to-Spanish and Spanish-to-Basque machine translation in the clinical domain. The treatment of these "typical errors" is made in a specific way by means of describing them using the two-level lexicon system. This extension consists basically of two features added to the standard formalism which allow the lexicon builder to make explicit the interdependencies of morphemes.User-lexicons can be interactively enriched with new entries enabling the checker from then on to recognize all the possible flexions derived from them.Due to a late process of standardization of the language, writers don't always know the standard form to be used and commit errors. This analyzer is taken as a basic tool for current and future work on automatic processing of Basque.An extension for continuation class specifications in order to deal with long-distance dependencies is proposed. This application is intended to cover a large part of the language.Because Basque is a highly inflected language, the approach of spelling checking and correction has been conceived as a by-product of a general purpose morphological. The application of the formalism of two-level morphology to Basque and its use in the elaboration of the XUXEN spelling checker/corrector are described. We demonstrate how a well-known problem of German morphology, so-called "Umlautung", can be described in our approach in a linguistically motivated and efficient way. Namely we propose to restrict the applicability of two-level rules by providing them with filters in the form of feature structures. ![]() In this paper we describe an extension to the model which will allow for the description of such phenomena. But up to now no linguistically satisfying solution has been proposed for the treatment of non-concatenative morphology in such a framework. ![]() ![]() Bear 1988a, Carson 1988, Görz & Paulus 1988, Schiller & Steffens 1990) to overcome the shortcomings of the continuation-classes originally proposed by Koskenniemi (1983) and Karttunen (1983) for the description of morphosyntax. Both parts rely on the same morph lexicon.Combinations of two-level morphology with feature-based morphosyntactic grammars have already been proposed by several authors (c.f. affixation) we make use of a grammar based on feature-unification. For the concatenative part of morphosyntax (i.e. The treatment of morphonology and non-concatenative morphology is based on the two-level approach originally proposed by Koskenniemi (1983). We call it hybrid because it consists of two separate parts interacting with each other in a well-defined way. In this paper we describe a hybrid system for morphological analysis and synthesis. Due to a late process of standardization of the language. User-lexicons can be interactively enriched with new entries enabling the checker from then on to recognize all the possible flexions derived from them. This extension consists basically of two features added to the standard formalism which allow the lexicon builder to make explicit the interdependencies of morphemes. An extension for continuation class specifications in order to deal with long-distance dependencies is proposed. This analyzer is taken as a basic tool for current and future work on automatic processing of Basque. Because Basque is a highly inflected language, the approach of spelling checking and correction has been conceived as a by-product of a general purpose morphological analyzer/generator. This application is intended to cover a large part of the language. ![]()
0 Comments
Leave a Reply. |