Research Papers

The development of innovative language technology is inconceivable without scientific research. At Linguatec, a top-class team of computer linguists and linguistic scientists press ahead with the research on machine translation, speech recognition and voice output. The following publications reflect the scientific commitment of Linguatec.

• Gregor Thurmair, 2006: Using Corpus Information to Improve MT Quality. in: Proc. Workshop LR4Trans-III, LREC Genova.


• Gregor Thurmair, 2006: Exchange Formats: TBX, OLIF and beyond. in: LDV-Forum 21,1, 45-56.


• Liu Lezhong, 2006: A Corpus-based Approach to Chinese Word Segmentation. Ludwig-Maximilian-University, Faculty for Language and Linguistics, Munich. National Bibliography Number: de:bvb:19-56621


• Gregor Thurmair, 2005: Hybrid Architectures for Machine Translation Systems. in: Language Resources and Evaluation 39, 1, 91-108.


• Gregor Thurmair, 2005: Sprachtechnologie in einem Informationssystem. In: Eibl. M., Wolff, Chr., Womser-Hacker, Ch., Hsg.: Designing Information Systems, Festschr. J. Krause. Konstanz (UVK), 127-143.


• Gregor Thurmair, 2005: Comparing rule-based and statistical MT output. Proc. ELRA HLT Evaluation Workshop, Malta (invited talk).


• Gregor Thurmair, 2005: Improving Machine Translation Quality. Proc. MT Summit X, Phuket (invited talk).


• Gregor Thurmair, 2004: Multilingual Content Processing. Proc. LREC 2004, Lissabon (keynote talk).


• Gregor Thurmair, 2004: Issues When Building CLIR Applications. Proc. CLEF Workshop 2004, Bath, UK (invited talk).


• Gregor Thurmair, 2004: Rule-based and Statistical Machine Translation. Proc. ASLIB, London (invited talk).


• Gregor Thurmair, 2004: Comparing rule-based and statistical MT output. Proc. LREC 2004 Workshop on The Amazing Utility of Parallel and Comparable Corpora. Proc. LREC Lissabon.