Neural Network Language Models for Translation with Limited Data

Authors:
Maxim Khalilov;José A. R. Fonollosa;F. Zamora-Martínez;M. J. Castro-Bleda;S. España-Boquera
Affiliations:
-;-;-;-;-
Venue:
ICTAI '08 Proceedings of the 2008 20th IEEE International Conference on Tools with Artificial Intelligence - Volume 02
Year:
2008

Citing 0
Cited 4

UCH-UPV English: Spanish system for WMT10

WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Approach of English to Sanskrit machine translation based on case-based reasoning, artificial neural networks and translation rules

International Journal of Knowledge Engineering and Soft Data Paradigms
Automatic Language Translation: An Enhancement to the Mobile Messaging Services

International Journal of Technology and Human Interaction
Rule-based approach for handling of case markers in English to Urdu/Hindi translation

International Journal of Knowledge Engineering and Soft Data Paradigms

Quantified Score

Hi-index	0.00

Visualization

Abstract

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 (Ngram 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.