Low-Resource Machine Translation Using MATREX: The DCU Machine Translation System for IWSLT 2009
Year: 2009
Type: conference-paper
Abstract: In this paper, we give a description of the Machine Trans-lation (MT) system developed at DCU that was used for our fourth participation in the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT 2009). Two techniques are deployed in our system in order to improve the translation quality in a low-resource scenario. The first technique is to use multiple segmenta-tions in MT training and to utilise word lattices in decoding stage. The second technique is used to select the optimal training data that can be used to build MT systems. In this year’s participation, we use three different prototype SMT systems, and the output from each system are combined us-ing standard system combination method. Our system is the top system for Chinese–English CHALLENGE task in terms of BLEU score. 1.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2103873751