This article advances the idea of establishing an English item pool and a system of preparing questions by adopting group technology, states the basic principle of establishing an item pool and the implementation procedure of the system, and analyzes through examples the advantages of the system.

The research on bilingual corpora is one of the most important topics in the field of natural language processing.

This paper focuses on extracting translation pairs from unaligned Chinese English bilingual corpora.

Experimental Research of Constructing Chinese and Uighur Bilingual Corpus;

To support an ongoing Chinese-English machine translation project, a Chinese English bilingual corpus is being set up.

This paper first investigates 4 co occurrence based models which are most often used to calculate word translation probabilities in bilingual corpus, and then proposes a machine aided dictionary compilation system based on log likelihood and iterative size reduction.

The Machine Translation Units extracted from the bilingual corpora can cover the natural language text even more.

In this paper, based on large scale bilingual corpora and the theory of vector space model and lexical mutual information, the traditional mono-language IR technology is applied to convert the challenge of translation of query keyword.