Paper: TICCLops: Text-Induced Corpus Clean-up as online processing system

ACL ID C14-2012
Title TICCLops: Text-Induced Corpus Clean-up as online processing system
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2014
Authors

We present the ?online processing system? version of Text-Induced Corpus Clean-up, a web service and application open for use to researchers. The system has over the past years been developed to provide mainly OCR error post-correction, but can just as fruitfully be employed to automatically correct texts for spelling errors, or to transcribe texts in an older spelling into the modern variant of the language. It has recently been re-implemented as a distributable and scalable software system in C++, designed to be easily adaptable for use with a broad range of languages and diachronical language varieties. Its new code base is now fit for production work and to be released as open source.