With a few exceptions, discriminative training in statistical machine translation (SMT) has been content with tuning weights for large feature sets on small development data. Evid...
When a database query has a large number of results, the user can only be shown one page of results at a time. One popular approach is to rank results such that the "best&quo...
The AVENUE project contains a run-time machine translation program that is surrounded by pre- and post-run-time modules. The post-run-time module selects among translation alternat...
Katharina Probst, Lori S. Levin, Erik Peterson, Al...
This paper proposes a two-phase example-based machine translation methodology which develops translation templates from examples and then translates using template matching. This ...
This paper proposes a learning method of translation rules from parallel corpora. This method applies the maximum entropy principle to a probabilistic model of translation rules. ...