International Workshop on Spoken Language Translation (IWSLT) 2010

Paris, France
December 2-3, 2010

UPC-BMIC-VDU System Description for the IWSLT 2010: Testing Several Collocation Segmentations in a Phrase-Based SMT System

Carlos A. Henríquez (1), Marta R. Costa-jussà (2), Vidas Daudaravicius (3), Rafael E. Banchs (4), José B. Marino (1)

1TALP Research Center, Universitat Politècnica de Catalunya, Barcelona, Spain
(2) Barcelona Media Innovation Center, Barcelona, Spain
(3) Vytautas Magnus University, Kaunas, Lithuania
(4) Institute for Infocomm Research, Singapore

This paper describes the UPC-BMIC-VMU participation in the IWSLT 2010 evaluation campaign. The SMT system is a standard phrase-based enriched with novel segmentations. These novel segmentations are computed using statistical measures such as Log-likelihood, T-score, Chi-squared, Dice, Mutual Information or Gravity-Counts.
   The analysis of translation results allows to divide measures into three groups. First, Log-likelihood, Chi-squared and T-score tend to combine high frequency words and collocation segments are very short. They improve the SMT system by adding new translation units. Second, Mutual Information and Dice tend to combine low frequency words and collocation segments are short. They improve the SMT system by smoothing the translation units. And third, Gravity- Counts tends to combine high and low frequency words and collocation segments are long. However, in this case, the SMT system is not improved.
   Thus, the road-map for translation system improvement is to introduce new phrases with either low frequency or high frequency words. It is hard to introduce new phrases with low and high frequency words in order to improve translation quality. Experimental results are reported in the Frenchto- English IWSLT 2010 evaluation where our system was ranked 3rd out of nine systems.

Full Paper

Bibliographic reference.  Henríquez, Carlos A. / Costa-jussà, Marta R. / Daudaravicius, Vidas / Banchs, Rafael E. / Marino, José B. (2010): "UPC-BMIC-VDU system description for the IWSLT 2010: testing several collocation segmentations in a phrase-based SMT system", In IWSLT-2010, 189-195.