Full text
|
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (231kB) | Preview |
Lopez Ludeña, Veronica and San Segundo Hernández, Rubén and Montero Martínez, Juan Manuel (2012). UPM system for WMT 2012. In: "7th Workshop on Statistical Machine Translation", 07/06/2012 - 08/06/2012, Montréal, Canada. pp. 338-344.
Title: | UPM system for WMT 2012 |
---|---|
Author/s: |
|
Item Type: | Presentation at Congress or Conference (Article) |
Event Title: | 7th Workshop on Statistical Machine Translation |
Event Dates: | 07/06/2012 - 08/06/2012 |
Event Location: | Montréal, Canada |
Title of Book: | Workshop on Statistical Machine Translation |
Date: | 2012 |
Subjects: | |
Faculty: | E.T.S.I. Telecomunicación (UPM) |
Department: | Ingeniería Electrónica |
Creative Commons Licenses: | Recognition - No derivative works - Non commercial |
|
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (231kB) | Preview |
This paper describes the UPM system for the Spanish-English translation task at the NAACL 2012 workshop on statistical machine translation. This system is based on Moses. We have used all available free corpora, cleaning and deleting some repetitions. In this paper, we also propose a technique for selecting the sentences for tuning the system. This technique is based on the similarity with the sentences to translate. With our approach, we improve the BLEU score from 28.37% to 28.57%. And as a result of the WMT12 challenge we have obtained a 31.80% BLEU with the 2012 test set. Finally, we explain different experiments that we have carried out after the competition.
Item ID: | 20374 |
---|---|
DC Identifier: | https://oa.upm.es/20374/ |
OAI Identifier: | oai:oa.upm.es:20374 |
Deposited by: | Memoria Investigacion |
Deposited on: | 02 Oct 2013 18:18 |
Last Modified: | 21 Apr 2016 23:07 |