PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Online Learning for Interactive Statistical Machine Translation
Daniel Ortiz-Martínez, Ismael García-Varea and Francisco Casacuberta
In: NAACL HLT 2010, June 1–6, Los Angeles., USA.

Abstract

State-of-the-art Machine Translation (MT) systems are still far from being perfect. An alternative is the so-called Interactive Machine Translation (IMT) framework. In this framework, the knowledge of a human translator is combined with a MT system. The vast majority of the existing work on IMT makes use of the well-known emphbatch learning paradigm. In the batch learning paradigm, the training of the IMT system and the interactive translation process are carried out in separate stages. This paradigm is not able to take advantage of the new knowledge produced by the user of the IMT system. In this paper, we present an application of the emphonline learning paradigm to the IMT framework. In the online learning paradigm, the training and prediction stages are no longer separated. This feature is particularly useful in IMT since it allows the user feedback to be taken into account. The online learning techniques proposed here incrementally update the statistical models involved in the translation process. Empirical results show the great potential of online learning in the IMT framework

EPrint Type:Conference or Workshop Item (Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:7439
Deposited By:Alfons Juan
Deposited On:17 March 2011