Resumen de Lexicografía computacional y pares de lenguas con reducidos recursos
In this article, we present a set of computational methods based on corpora or on the extraction of data from existing lexical resources for drafting bilingual dictionary content. These methods operate on three structural levels: (1) lemma lists, (2) syntactic entities, and (3) translation equivalents. The escribed methods are applied to the language pair German-Basque. Our motivation is twofold: first, to reduce the amount of manual work in the lexicographical process and, second, to contribute to the enrichment of the resources used for drafting. We also discuss the possibility of obtaining translated usage examples from parallel corpora.
