integrated chinese word segmentation in statistical machine translation jia xu and evgeny matusov and richard zens and hermann ney lehrstuhl fur informatik vi computer science department rwthaachenuniversity d 52056aachen germany ...
Filetype PDF | Posted on 21 Sep 2022 | 4 years ago
The words contained in this file might help you see if this file matches what you are looking for:
...Integrated chinese word segmentation in statistical machine translation jia xu and evgeny matusov richard zens hermann ney lehrstuhl fur informatik vi computer science department rwthaachenuniversity d aachen germany xujia cs rwth de abstract onemaycontainerrorsormaybenotoptimalwithrespectto achinese sentence is represented as a sequence of charac the training corpus ters words are not separated from each other statisti instead reading single best segmented our cal conventional approach to seg system handles all alternatives by ment character into during lattice similar approaches were applied pre processing performed speech e g where recognition afterwards however this method optimal for two rea text combined using sons segmentations may be erroneous lattices we also weight different with given depends on language model trained at its context level weighting order minimize errors take dif cost was introduced ferent segmen verify improvements tation account integrate process experiment...