On the basis of the supposition that the causative structures are composed of two propositions, one of which is causer, the other is the result, we adopted Dowty s bisentential analysis to describe and interpret Chinese causative structures in the framework of Minimalist Program.

Generalized LR syntactic analysis algorithm based on neural network;

The capital theory is discussed firstly,based on the theory a syntactic analysis of machine translation method is proposed.

This thesis focuses on the syntactic analysis of the raising verb under raising construction in GB.

The nucleus inference based the Chinese syntax analysis;

The Design and Implementation of Syntax Analysis System Based on Chart Algorithm;

A design of expert system of syntax analysis in Chinese based on neural networks is proposed.

Research on method of syntax parsing based on statistical approach;

To decrease the difficulty of syntax parsing,an improved Viterbi algorithm to recognize phrases in Chinese texts based on the corpus from Peking university and Harbin institute of technology is adopted.

The identification of this phrase has great value for NLPS such as syntax parsing,machine translation.

Reaserch on Dependency Parsing of Chinese Simple Sentence;

This paper presents the experiences in parsing for several machine translation systems,and proposes a modular parser using combination of statistic and rule methods.

Source language analysis is core of MT, and includes morphology analysis, parsing and semantic analysis.

Based on a large amount of rightly parsed examples with which both parsing procedures and parsing results are recorded,syntactic parsing can be carried out by searching similar example or fragment,and matching similar language structure and analysis in the examples.

Chinese syntactic parsing is a key of Chinese study and Chinese information processing,as well as a difficulty.

The output of syntactic parsing is used in this method to extract the Subject-Predicate structure as well as interrogative words and their adjunctive parts as features for classification,leading to substantial reduction in noise,and emphasis on the main features of quest.