Title The DeepThought Core Architecture Framework
Author(s) Ulrich Callmeier (1), Andreas Eisele (1), Ulrich Schäfer (2), Melanie Siegel (1)

(1) Computational Linguistics Department, Saarland University, P.O.Box 151150, D-66041 Saarbruecken, Germany; (1) Language Technology Lab, German Research Center for Artificial Intelligence (DFKI GmbH), Stuhlsatzenhausweg 3, D-66123 Saarbruecken, Germany

Session P13-W
Abstract The research performed in the DeepThought project aims at demonstrating the potential of deep linguistic processing if combined with shallow methods for robustness. Classical information retrieval is extended by high precision concept indexing and relation detection. On the basis of this approach, the feasibility of three ambitious applications will be demonstrated, namely: precise information extraction for business intelligence; email response management for customer relationship management; creativity support for document production and collective brainstorming. Common to these applications, and the basis for their development is the XML-based, RMRS-enabled core architecture framework that will be described in detail in this paper. The framework is not limited to the applications envisaged in the DeepThought project, but can also be employed e.g. to generate and make use of XML standoff annotation of documents and linguistic corpora, and in general for a wide range of NLP-based applications and research purposes.
Keyword(s) NLP Application, NLP Architecture, Deep and Shallow NLP Processing, Question Answering, Evaluation, Robust Semantics, XML
Language(s) English, German
Full Paper 603.pdf