Paper: Generalized Graphical Abstractions for Statistical Machine Translation

ACL ID N07-2009
Title Generalized Graphical Abstractions for Statistical Machine Translation
Venue Human Language Technologies
Session Short Paper
Year 2007
Authors

ons for Statistical Machine Translation Karim Filali and Jeff Bilmes∗ Departments of Computer Science & Engineering and Electrical Engineering University of Washington Seattle, WA 98195, USA {karim@cs,bilmes@ee}.washington.edu Abstract We introduce a novel framework for the expression, rapid-prototyping, and eval- uation of statistical machine-translation (MT) systems using graphical mod- els. The framework extends dynamic Bayesian networks with multiple con- nected different-length streams, switching variable existence and dependence mech- anisms, and constraint factors. We have implemented a new general-purpose MT training/decoding system in this frame- work, and have tested this on a variety of existing MT models (including the 4 IBM models), and some novel ones as well, all using Eur...