Evaluation of a Language Identification System for Mono- and Multi-lingual Text Documents

Abstract(s)

Language identification an important task for web information retrieval. This paper presents the implementation of a tool for language identification in mono- and multilingual documents. The tool implements four algorithms for language identification. Furthermore, we present a n-gram approach for the identification of languages in multi-lingual documents. An evaluation for monolingual texts of varied length is presented. Results for eight languages including Ukrainian and Russian are shown. It could be shown that n-gram-based approaches outperform word-based algorithms for short texts. For longer texts, the performance is comparable. The evaluation for multilingual documents is based on both short synthetic documents and real world web documents. Our tool is able to recognize the languages present as well as the location of the language change with reasonable accuracy.