Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
This paper describes an all level approach on statistical natural language translation (SNLT). W i t h o u t any predefined knowledge the system learns a statistical translation lexicon (STL), word classes (WCs) and translation rules (TRs) from a parallel corpus thereby producing a generalized form of a word alignment (WA). The translation process itself is realized as a beam search. In our method example-based techniques enter an overall statistical approach leading to about 50 percent correctly translated sentences applied to the very difficult EnglishGerman V E R B M O B I L spontaneous speech corpus. . | Improving Statistical Natural Language Translation with Categories and Rules Franz Josef Och and Hans Weber FAU Erlangen - Computer Science Institute IMMD VIII - Artificial Intelligence Am Weichselgarten 9 91058 Erlangen - Tennenlohe Germany faoch weber @inund8.informatik.uni-erlangen.de Abstract This paper describes an all level approach on statistical natural language translation SNLT . Without any predefined knowledge the system learns a statistical translation lexicon STL word classes WCs and translation rules TRs from a parallel corpus thereby producing a generalized form of a word alignment WA . The translation process itself is realized as a beam search. In our method example-based techniques enter an overall statistical approach leading to about 50 percent correctly translated sentences applied to the very difficult English-German Verbmobil spontaneous speech corpus. 1 Introduction In SNLT the transfer itself is realized as a maximization process of the form Trans d argmaxe P e d 1 Here d is a given source language SL sentence which has to be translated into a target language TL sentence e. In order to model the distributions P e d all approaches in SNLT use a divide and conquer strategy of approximating P e d by a combination of simpler models. The problem is to reduce parameters in a sufficient way but end up with a model still able to describe the linguistic facts of natural language translation. The work presented here uses two approximations for P e d . One approximation is used for to gain the relevant parameters in training while a modified formula is subject of decoding translations. In detail we impose the following modifications with respect to approaches published in the last decade 1. A refined distance weight for the STL probabilities is used which allows for a good modeling of the effects caused by syntactic phrases. 2. In order to account for collocations a WA technique is used where one-to-n and n-to-one WAs are allowed. 3. For the .
