Title: Learning Machine Translation from In-domain and Out-of-domain Data
Authors: TURCHI MARCOGOUTTE CyrilCRISTIANINI Nello
Publisher: European Association for Machine Translation
Publication Year: 2012
JRC N°: JRC73480
URI: http://publications.jrc.ec.europa.eu/repository/handle/JRC73480
Type: Articles in periodicals and books
Abstract: The performance of Phrase-Based Statistical Machine Translation (PBSMT) systems mostly depends on training data. Many papers have investigated how to create new resources in order to increase the size of the training corpus in an attempt to improve PBSMT performance. In this work, we analyse and characterize the way in which the in-domain and out-of-domain performance of PBSMT is impacted when the amount of training data increases. Two different PBSMT systems, Moses and Portage, two of the largest parallel corpora, Giga (French-English) and UN (Chinese-English) datasets and several in- and out-of-domain test sets were used to build high quality learning curves showing consistent logarithmic growth in performance. These results are stable across language pairs, PBSMT systems and domains. We also analyse the respective impact of additional training data for estimating the language and translation models. Our proposed model approximates learning curves very well and indicates the translation model contributes about 30\% more to the performance gain than the language model.
JRC Directorate:Space, Security and Migration

Files in This Item:
There are no files associated with this item.


Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.