Phrase-Based ITG decoder
In this master thesis we implement a MT decoder that use the main strenghts of syntax and phrase based approaches. The decoder has two parts: a parser that obtains the syntactic tree, and a tree-tostring method to find the most likely target-language sentence. Finally, we present experiments over tw...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2008 |
| País: | España |
| Institución: | Universitat Politècnica de València (UPV) |
| Repositorio: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia |
| Idioma: | inglés |
| OAI Identifier: | oai:riunet.upv.es:10251/13296 |
| Acceso en línea: | https://riunet.upv.es/handle/10251/13296 |
| Access Level: | acceso abierto |
| Palabra clave: | Machine translation Syntax Phrase-based decoder Itg LENGUAJES Y SISTEMAS INFORMATICOS Máster Universitario en Inteligencia Artificial, Reconocimiento de Formas e Imagen Digital-Màster Universitari en Intel·ligència Artificial, Reconeixement de Formes i Imatge Digital |
| Sumario: | In this master thesis we implement a MT decoder that use the main strenghts of syntax and phrase based approaches. The decoder has two parts: a parser that obtains the syntactic tree, and a tree-tostring method to find the most likely target-language sentence. Finally, we present experiments over two corpora Spanish-English and German-English. |
|---|