tr-announce

Download

tr-announce@lists.rwth-aachen.de

May 2003

1 participants
2 discussions

2003-06: Statistical Machine Translation: From Single-Word Models to Alignment Templates
by Volker Stolz 24 May '03

24 May '03

The following technical report is available from http://aib.informatik.rwth-aachen.de/: Franz Josef Och Statistical Machine Translation: From Single-Word Models to Alignment Templates 2003-06 In this work, new approaches for machine translation using statistical methods are described. In addition to the standard source-channel approach to statistical machine translation, a more general approach based on the maximum entropy principle is presented. Various methods for computing single-word alignments using statistical or heuristic models are described. Various smoothing techniques, methods to integrate a conventional dictionary and training methods are analyzed. A detailed evaluation of these models is performed by comparing the automatically produced word alignment with a manually produced reference alignment. Based on these fundamental single-word based alignment models, a new phrase-based translation model - the alignment template model - is suggested. For this model, a training and an efficient search algorithm is developed. For two specific applications (interactive translation and multi-source translation) specific search algorithms are developed. The suggested machine translation approach has been tested for the German-English Verbmobil task, the French-English Hansards task and for Chinese-English news text translation. Often, the obtained results have been significantly better than those obtained with alternative approaches to machine translation. Regards, Volker

1 0

2003-04: Improving Dependency Pairs
by Volker Stolz 20 May '03

20 May '03

The following technical report is available from http://aib.informatik.rwth-aachen.de/: Jürgen Giesl, René Thiemann, Peter Schneider-Kamp and Stephan Falke Improving Dependency Pairs 2003-04 Abstract: The dependency pair approach is one of the most powerful techniques for termination and innermost termination proofs of term rewrite systems (TRSs). For any TRS, it generates inequality constraints that have to be satisfied by weakly monotonic well-founded orders. We improve the dependency pair approach by considerably reducing the number of constraints produced for (innermost) termination proofs. Moreover, we extend transformation techniques to manipulate dependency pairs which simplify (innermost) termination proofs significantly. In order to fully automate the dependency pair approach, we show how transformation techniques and the search for suitable orders can be mechanized efficiently. We implemented our results in the automated termination prover AProVE and evaluated them on large collections of examples. Regards, Volker

1 0