Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Artículo científico |
| Lenguaje: | en |
| Publicado: |
Instituto Politécnico Nacional
2015
|
| Materias: | |
| Acceso en línea: | https://www.redalyc.org/articulo.oa?id=61539886012 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Tabla de Contenidos:
- Segmentation Strategies to Face Morphology Challenges in Brazilian-Portuguese/English Statistical Machine Translation and Its Integration in Cross-Language Information Retrieval Marta R. Costa-jussá Computación cross lation factored Morphology based machine trans The use of morphology is particularly inter- esting in the context of statistical machine translation in order to reduce data sparseness and compensate a lack of training corpus. In this work, we propose several approaches to introduce morphology knowledge into a standard phrase-based machine translation sys- tem. We provide word segmentation using two differ- ent tools ( COGROO and MORFESSOR ) which allow re- ducing the vocabulary and data sparseness. Then, to these segmentations we add the morphological in- formation of a POS language model. We combine all these approaches using a Minimum Bayes Risk strat- egy. Experiments show significant improvements from the enhanced system over the baseline system on the Brazilian-Portuguese/English language pair. Finally, we report a case study of the impact of enhancing the sta- tistical machine translation system with morphology in a cross-language application system such as ONAIR which allows users to look for information in video fragments through queries in natural language. 2015 artículo científico 1405-5546 https://www.redalyc.org/articulo.oa?id=61539886012 en http://www.redalyc.org/revista.oa?id=615 Computación y Sistemas application/pdf Instituto Politécnico Nacional Computación y Sistemas (México) Num.2 Vol.19