Publication
Content Quality Management with Open Source Language Technology
Felix Sasaki; Christian Lieske
tcworld conference 2011, 10/2011.
Abstract
This text - a complement to the corresponding tutorial at the tcWorld 2011 - starts with an overview of typical linguistic quality tasks related to textual content. Afterwards - following a short explanation of general NLP/LT concepts - it sketches NLP/LT for linguistic quality tasks. As a basis for sustainable and solid NLP/LT, so-called Text Technology is being surveyed. The text then moves on to observations related to the use of NLP/LT in real world deployment scenarios.
The concepts are exemplified based on the reality in some technical communications environments with open source offerings. In order to allow for easy follow-up, the demonstrations use open source technology. Some tasks use examples from the realm of language-related requirements related to accessibility (sometimes referred to as easy/simple language).