Computerlinguistik in der Dolmetschpraxis unter besonderer Berücksichtigung der Korpusanalyse

Abstract

This contribution demonstrates an even more practice-oriented exploitation of corpora, both monolingual and parallel. It describes the design of a software, InterpretBank, which supports conference interpreters in all stages of their work. Based on Baroni and Bernardini’s (2004) BootCat mechanism, the program harvests the web for domain-specific documents given a set of search terms, performs term extraction on them and uses additional resources, e.g. Wikipedia or bilingual online dictionaries, to propose definitions, translations, collocations and keyword-in-context information. All available modules, for harvesting, management and retrieval, are adapted to the specific needs of interpreters, reducing the time needed for preparation and allowing for efficient retrieval while interpreting. A pilot module adds the possibility to include parallel resources, e.g. translation memories or the OPUS corpora, in the preparation phase.