The importance of MT for the survival of minority languages: Spanish-Galician MT system

THE IMPORTANCE OF MT FOR THE SURVIVAL OF MINORITY LANGUAGES: SPANISH-GALICIAN MT SYSTEM Inés Diz Gamallo Centro Ramón Piñeiro para a Investigación en Humanidades1 / University of Vigo (Spain) Estrada Santiago-Noia, Km 3. A Barcia-Santiago de Compostela (Spain) / As Lagoas - Marcosende s/n, Vigo (Spain) idiz@cirp.es ABSTRACT Our society is coming through a lot of changes that are connected, basically, with information. Maybe those languages that are present in this challenge will survive, and languages that will not meet those changes will dissapear. The Linguistics section of the Centro Ramón Piñeiro para a Investigación en Humanidades (CRP) is devoted to the development of basic language resources for Galician for trying to solve the gap existing in computational resources and to made it possible for Galician to be present in the new information society. The aim of this paper is to explain how we have developed a Spanish-Galician Machine Translation system, what tools we have made use of, which difficulties we have found in our task and what are the final results of the project. KEYWORDS Minority languages, machine translation, basic computational resources, formal grammar, lexicon, corpora. 1 “Ramón Piñeiro” Centre for Humanities Research INTRODUCTION In the information society in which we are living, the status of "major" and minority languages is very different. Our society is coming through a lot of changes, and these changes are connected, basically, with information. Maybe languages that are present in this challenge will survive, and languages that will not meet those changes will disappear. It sounds dramatic, but we think that this is very likely to happen. It is for that reason that minority languages have to be ready to assume this challenge, even though they are in disadvantage with respect to "major" languages. To overcome this challenge, minority languages need to have not only basic computational resources (lemmatizers, lexicons, corpora, parsers....), but also some other more elaborated resources, such as information retrieval systems, voice recognizers/synthetizers or machine translation systems (Somers, 1997) The Galician language is a minority language. Despite its similarity to Portuguese, it is only a few years ago since a machine readable dictionary and a spell checker are available, and no grammar checker has yet been made. But this is not the only problem. There are other important handicaps, like the lack of studies (non computational studies, but general studies) on some aspects of Galician language, like syntax or semantics in which anyone can base his computational work. As you could imagine, in a situation like this (similar to another minority languages), the task to generate computational resources is necessary harder. The Linguistics section of the Centro Ramón Piñeiro para a Investigación en Humanidades (CRP), directed by Guillermo Rojo, is devoted to the development of basic language resources for Galician, such as taggers, parsers, corpora and lexicons for trying to solve this gap and to made it possible for Galician to be present in the new information society. The aim of this paper is to explain how we have developed …

Content truncated to 500 words