Accession Number:

AD1028958

Title:

Phrase Based Decoding using a Discriminative Model

Descriptive Note:

Conference Paper

Corporate Author:

International Institute of Information Technology, Hyderabad Hyderabad India

Personal Author(s):

• Bangalore,Srinivas
• Kolachina,Prasanth
• Kolachina,Sudheer
• Sriram,Venkatapathy
• PVS,Avinesh

Report Date:

2010-08-28

Pagination or Media Count:

9.0

Abstract:

In this paper, we present an approach to statistical machine translation that combines the power of a discriminative model for training a model for Machine Translation, and the standard beam-search based decoding technique for the translation of an input sentence. A discriminative approach for learning lexical selection and reordering utilizes a large set of feature functions thereby providing the power to incorporate greater contextual and linguistic information, which leads to an effective training of these models. This model is then used by the standard state-of-art Moses decoder Koehn et al., 2007 for the translation of an input sentence. We conducted our experiments on Spanish-English language pair. We used maximum entropy model in our experiments. We show that the performance of our approach using simple lexical features is comparable to that of the state-of-art statistical MT system Koehn et al., 2007. When additional syntactic features POS tags in this paper are used, there is a boost in the performance which is likely to improve when richer syntactic features are incorporated in the model.

Descriptors:

• computational linguistics
• natural language computing
• machine translation
• natural language understanding
• algorithms
• machine learning
• probability distributions
• accuracy

Subject Categories:

Distribution Statement:

APPROVED FOR PUBLIC RELEASE