A set of Tools for Integrating Linguistic and Non-Linguistic Information

In this position paper we describe the actual state of the development of an integrated set of tools (called SCHUG) for language processing supporting interaction with disparate sources of information, making thus Natural Language Processing (NLP) and Human Language Technology (HLT) even more relevant for Information Technology (IT) applications. The set of tools is realizing the communication with non language-based devices and services via XML machine readable annotations. Non-linguistic information, in most of the cases domain-specific knowledge, can thus be straightforward included in the linguistically analysed texts, and so contribute to a knowledge markup of textual documents. The basic language technology guiding this markup is Information Extraction (IE) and the added information can be made visible by means of automatic hyperlinking and visualization techniques.