Semi-Automatic Indexing of Multilingual Documents

TL;DR

This paper introduces a semi-automatic method for indexing multilingual electronic documents, utilizing dictionaries and user input to resolve ambiguities, build a multilingual thesaurus, and improve information retrieval across languages.

Contribution

It presents a novel semi-automatic approach for creating and updating a multilingual thesaurus to enhance document indexing and retrieval in digital libraries.

Findings

Effective handling of multilingual document indexing

Incremental updating of the multilingual thesaurus

Improved retrieval accuracy across languages

Abstract

With the growing significance of digital libraries and the Internet, more and more electronic texts become accessible to a wide and geographically disperse public. This requires adequate tools to facilitate indexing, storage, and retrieval of documents written in different languages. We present a method for semi-automatic indexing of electronic documents and construction of a multilingual thesaurus, which can be used for query formulation and information retrieval. We use special dictionaries and user interaction in order to solve ambiguities and find adequate canonical terms in the language and adequate abstract language-independent terms. The abstract thesaurus is updated incrementally by new indexed documents and is used to search document concerning terms in a query to the document base.