Mostra el registre d'ítem simple
Robust Estimation of Feature Weights in Statistical Machine Translation
dc.contributor.author | España Bonet, Cristina |
dc.contributor.author | Màrquez Villodre, Lluís |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics |
dc.date.accessioned | 2010-11-29T12:55:11Z |
dc.date.available | 2010-11-29T12:55:11Z |
dc.date.created | 2010 |
dc.date.issued | 2010 |
dc.identifier.citation | España-Bonet, C.; Màrquez, L. Robust estimation of feature weights in statistical machine translation. A: Annual Conference of the European Association for Machine Translation. "14th Annual Conference of the European Association for Machine Translation". Saint-Raphaël: 2010, p. 190-197. |
dc.identifier.uri | http://hdl.handle.net/2117/10449 |
dc.description.abstract | Weights of the various components in a standard Statistical Machine Translation model are usually estimated via Minimum Error Rate Training. With this, one finds their optimum value on a development set with the expectation that these optimal weights generalise well to other test sets. However, this is not always the case when domains differ. This work uses a perceptron algorithm to learn more robust weights to be used on out-of-domain corpora without the need for specialised data. For an Arabic-to-English translation system, the generalisation of weights represents an improvement of more than 2 points of BLEU with respect to the MERT baseline using the same information. |
dc.format.extent | 8 p. |
dc.language.iso | eng |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural |
dc.subject.lcsh | Statistical Machine Translation System (model) |
dc.subject.lcsh | Machine translation |
dc.subject.lcsh | Arabic language -- Translating into English |
dc.title | Robust Estimation of Feature Weights in Statistical Machine Translation |
dc.type | Conference lecture |
dc.subject.lemac | Traducció automàtica -- Mètodes estadístics |
dc.subject.lemac | Traductors (Programes d'ordinador) |
dc.contributor.group | Universitat Politècnica de Catalunya. GPLN - Grup de Processament del Llenguatge Natural |
dc.description.peerreviewed | Peer Reviewed |
dc.rights.access | Open Access |
local.identifier.drac | 3094769 |
dc.description.version | Postprint (published version) |
local.citation.author | España-Bonet, C.; Màrquez, L. |
local.citation.contributor | Annual Conference of the European Association for Machine Translation |
local.citation.pubplace | Saint-Raphaël |
local.citation.publicationName | 14th Annual Conference of the European Association for Machine Translation |
local.citation.startingPage | 190 |
local.citation.endingPage | 197 |