A New Cross-Language Commodity Information Retrieval Approach in Book Searching

This paper analyzes the basic modes of Cross-Language Information Retrieval (CLIR) and the critical technologies of translation disambiguation. It optimizes translation outcome by eliminating translation ambiguity. The methods are based on co-occurrences between pairs of terms as well as computing weights of terms. On this basis, we established a CLIR system for book searching. The experimental results show that the translation accuracy and the retrieval efficiency are improved.