Partial least squares for word confidence estimation in machine translation
We present a new technique to estimate the reliability of the words in automatically generated translations. Our approach addresses confidence estimation as a classification problem where a confidence score is to be predicted from a feature vector that represents each translated word. We describe a...
| Autores: | , , |
|---|---|
| Tipo de recurso: | capítulo de libro |
| Fecha de publicación: | 2013 |
| 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:10251/39685 |
| Acceso en línea: | https://riunet.upv.es/handle/10251/39685 |
| Access Level: | acceso abierto |
| Palabra clave: | Machine translation Word confidence estimation Statistical multivariate analysis Partial least squares discriminant analysis ESTADISTICA E INVESTIGACION OPERATIVA LENGUAJES Y SISTEMAS INFORMATICOS |
| Sumario: | We present a new technique to estimate the reliability of the words in automatically generated translations. Our approach addresses confidence estimation as a classification problem where a confidence score is to be predicted from a feature vector that represents each translated word. We describe a new set of prediction features designed to capture context information, and propose a model based on partial least squares to perform the classification. Good empirical results are reported in a large-domain news translation task. |
|---|