Title:
|
Robust Estimation of Feature Weights in Statistical Machine Translation
|
Author:
|
España Bonet, Cristina; Màrquez Villodre, Lluís
|
Other authors:
|
Universitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics; Universitat Politècnica de Catalunya. GPLN - Grup de Processament del Llenguatge Natural |
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. |
Abstract:
|
Peer Reviewed |
Subject(s):
|
-Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural -Statistical Machine Translation System (model) -Machine translation -Arabic language -- Translating into English -Traducció automàtica -- Mètodes estadístics -Traductors (Programes d'ordinador) |
Rights:
|
|
Document type:
|
Article - Published version Conference Object |
Share:
|
|