Neural Network Language Models for Translation with Limited Data

In this paper we present how to estimate a continuous space Language Model with a Neural Network to be used in a Statistical Machine Translation system. We report results for an Italian-English translation task obtained on a small corpus (about 150 K tokens), that can be considered a task with a lack of training data. Different word history length included in the connectionist language model (n-gram order) and distinct continuous space representation (i.e. words appearing in the training corpus more than k times) are considered in the study. The experimental results are evaluated by means of automatic evaluation metrics correlated with fluency and adequacy of the generated translations.

• Type: Conference
• Year: 2008
• Where: ICTAI
• Authors: Maxim Khalilov, José A. R. Fonollosa, Francisco Zamora-Martínez, María José Castro Bleda, Salvador España Boquera
• Keywords: Artificial Intelligence, Continuous Space, Continuous Space Language, ICTAI 2008, Italian-English Translation Task