Por favor utiliza este link para citar o compartir este documento:
http://repositoriodigital.academica.mx/jspui/handle/987654321/83060Full metadata record
| Campo DC | Valor | Lenguaje |
|---|---|---|
| dc.creator | Turchi,Marco | - |
| dc.creator | Ehrmann,Maud | - |
| dc.date | 2011-06-01 | - |
| dc.date.accessioned | 2012-07-31T17:22:33Z | - |
| dc.date.available | 2012-07-31T17:22:33Z | - |
| dc.date.issued | 2012-07-31 | - |
| dc.identifier | http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1870-90442011000100005 | - |
| dc.identifier.uri | http://repositoriodigital.academica.mx/jspui/handle/987654321/83060 | - |
| dc.description | Translation capability of a Phrase-Based Statistical Machine Translation (PBSMT) system mostly depends on parallel data and phrases that are not present in the training data are not correctly translated. This paper describes a method that efflciently expands the existing knowledge of a PBSMT system without adding more parallel data but using external morphological resources. A set of new phrase associations is added to translation and reordering models; each of them corresponds to a morphological variation of the source/target/both phrases of an existing association. New associations are generated using a string similarity score based on morphosyntactic information. We tested our approach on En-Fr and Fr-En translations and results showed improvements of the performance in terms of automatic scores (BLEU and Meteor) and reduction of out-of-vocabulary (OOV) words. We believe that our knowledge expansion framework is generic and could be used to add different types of information to the model. | - |
| dc.format | text/html | - |
| dc.language | en | - |
| dc.publisher | Polibits | - |
| dc.subject | Machine translation | - |
| dc.subject | knowledge | - |
| dc.subject | morphological resources | - |
| dc.title | Knowledge Expansion of a Statistical Machine Translation System using Morphological Resources | - |
| dc.type | journal article | - |
| Aparece en las Colecciones: | Polibits | |
Archivos de este documento:
No hay archivos asociados a este documento.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.