A Hybrid Machine Translation System for Typologically Related Languages

This paper describes a shallow parsing formalism aiming at machine translation between closely related languages. The formalism allows to write grammar rules helping to (partially) disambiguate chunks in input sentences. The chunks are then translatred into the target language without any deep syntactic or semantic processing. A stochastic ranker then selects the best translation according to the target language model. The results obtained for Czech and Slovak are presented.

• Type: Conference
• Year: 2008
• Where: FLAIRS
• Authors: Petr Homola, Vladislav Kubon
• Keywords: Artificial Intelligence, FLAIRS 2008, Shallow Parsing Formalism, Target Language, Target Language Model