Exploiting Rules for Word Sense Disambiguation in Machine Translation
Fuente:
Redalyc
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Artículo científico |
| Lenguaje: | en |
| Publicado: |
Sociedad Española para el Procesamiento del Lenguaje Natural
2005
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1876452267091034112 |
|---|---|
| author | Lucia Specia |
| author_facet | Lucia Specia |
| contents | Exploiting Rules for Word Sense Disambiguation in Machine Translation Lucia Specia Maria das Graças V. Nunes Mark Stevenson Computación rule evaluation machine learning Word sense disambiguation This paper describes the automatic generation and the evaluation of sets of rules for word sense disambiguation (WSD) in machine translation. The ultimate aim is to identify high-quality rules that can be used as knowledge sources in a relational WSD model. The evaluation was carried out both automatically, by means of four objective measures (error, coverage, support and novelty), and manually, by means of a subjective analysis of the level of interest of the best rules as pointed out by the objective measures. As a result, we selected 63 rules addressing seven highly ambiguous verbs. The evaluation also evidenced which kinds of knowledge were effectively used by the WSD rules, which are not always the same as those revealed by traditional evaluations of complete WSD models. Although we experimented with English-Portuguese, the rule generation and evaluation procedures could be applied to any language pair, provided that there is a disambiguation sample corpus for that language pair. 2005 artículo científico 1135-5948 https://www.redalyc.org/articulo.oa?id=515751735021 en http://www.redalyc.org/revista.oa?id=5157 Procesamiento del Lenguaje Natural application/pdf Sociedad Española para el Procesamiento del Lenguaje Natural Procesamiento del Lenguaje Natural (España) Num.35 |
| format | Artículo científico |
| id | redalyc_515751735021 |
| institution | Redalyc |
| language | en |
| publishDate | 2005 |
| publisher | Sociedad Española para el Procesamiento del Lenguaje Natural |
| spellingShingle | Exploiting Rules for Word Sense Disambiguation in Machine Translation Lucia Specia Computación rule evaluation machine learning Word sense disambiguation Exploiting Rules for Word Sense Disambiguation in Machine Translation Lucia Specia Maria das Graças V. Nunes Mark Stevenson Computación rule evaluation machine learning Word sense disambiguation This paper describes the automatic generation and the evaluation of sets of rules for word sense disambiguation (WSD) in machine translation. The ultimate aim is to identify high-quality rules that can be used as knowledge sources in a relational WSD model. The evaluation was carried out both automatically, by means of four objective measures (error, coverage, support and novelty), and manually, by means of a subjective analysis of the level of interest of the best rules as pointed out by the objective measures. As a result, we selected 63 rules addressing seven highly ambiguous verbs. The evaluation also evidenced which kinds of knowledge were effectively used by the WSD rules, which are not always the same as those revealed by traditional evaluations of complete WSD models. Although we experimented with English-Portuguese, the rule generation and evaluation procedures could be applied to any language pair, provided that there is a disambiguation sample corpus for that language pair. 2005 artículo científico 1135-5948 https://www.redalyc.org/articulo.oa?id=515751735021 en http://www.redalyc.org/revista.oa?id=5157 Procesamiento del Lenguaje Natural application/pdf Sociedad Española para el Procesamiento del Lenguaje Natural Procesamiento del Lenguaje Natural (España) Num.35 |
| title | Exploiting Rules for Word Sense Disambiguation in Machine Translation |
| topic | Computación rule evaluation machine learning Word sense disambiguation |
| url | https://www.redalyc.org/articulo.oa?id=515751735021 |