PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Multi-task minimum error rate training for SMT
Patrick Simianer, Katharina Wäschle and Stefan Riezler
The Prague Bulletin of Mathematical Linguistics Number 96, 2011.


We present experiments on multi-task learning for discriminative training in statistical machine translation (SMT), extending standard minimum-error-rate training (MERT) by techniques that take advantage of the similarity of related tasks. We apply our techniques to German-to-English translation of patents from 8 tasks according to the International Patent Classification (IPC) system. Our experiments show statistically significant gains over task-specific training by techniques that model commonalities through shared parameters. However, more finegrained combinations of shared parameters with task-specific ones could not be brought to bear on models with a small number of dense features. The software used in the experiments is released as open-source tool.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:8489
Deposited By:Sebastian Pado
Deposited On:16 February 2012