
handle: 10045/1303
Este artículo propone un método de extracción de equivalentes léxicos de traducción a partir de corpora paralelos alineados a niveles superiores a la oración y etiquetados morfosintácticamente. La estrategia que seguiremos toma en cuenta el efecto discriminante y desambiguador que el contexto local ejerce sobre un elemento léxico. Dada una palabra de la lengua fuente y un tipo de contexto particular, el método propuesto aprende la traducción de la palabra en ese tipo de contexto.
The paper proposes a method to extract translation equivalents from parallel corpora which were POS tagged and aligned using very large segments. The strategy we use takes into account the ability of contexts to select senses of words. Given a word of the source language and a particular type of context, we learn its word translation within an equivalent context.
Este trabajo ha sido subvencionado por el Ministerio de Educación y Ciencia a cargo del proyecto Gari-Coter, ref: HUM2004-05658-D02-02.
Corpora paralelos, Traducción, Translation, Multilingual lexical extraction, Parallel corpora, Extracción de léxico multilingüe
Corpora paralelos, Traducción, Translation, Multilingual lexical extraction, Parallel corpora, Extracción de léxico multilingüe
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
