A corpus-based approach for cross-lingual information retrieval.

摘要

With the increasing amount of online information, information retrieval systems must manage large volumes of data and information, often written in different languages and stored in different locations. This provides a challenge for crosslingual semantic interoperability since much of this information may be seemingly unconnected. How to generate an overview of this disparate data and information so that it can be analyzed, searched, summarized and visualized is problematic.; Currently, many approaches to retrieve textual materials from databases depend on a lexical match between words in users' requests and those in or assigned to documents in a database. Because of the tremendous diversity in the words people use to describe the same document, simple lexical matching methods are incomplete and imprecise. How to allow users to retrieve information on the basis of a conceptual topic or meaning of a document is an important issue. The creation of conceptual relationships would allow the system to deduce users' information needs correctly and retrieve relevant documents, even though the documents contain different terms from the queries. In addition, the queries may be written in languages other than English. The translation ambiguity significantly exacerbates the retrieval problem.