Paper: CL Research's Knowledge Management System

ACL ID P05-3004
Title CL Research's Knowledge Management System
Venue Annual Meeting of the Association of Computational Linguistics
Session System Demonstration
Year 2005
Authors

CL Research began experimenting with massive XML tagging of texts to answer questions in TREC 2002. In DUC 2003, the experiments were extended into text summarization. Based on these experiments, The Knowledge Management System (KMS) was developed to combine these two capabilities and to serve as a unified basis for other types of document exploration. KMS has been extended to include web question answering, both general and topic-based summarization, information extraction, and document exploration. The document exploration functionality includes identification of semantically similar concepts and dynamic ontology creation. As development of KMS has continued, user modeling has become a key research issue: how will different users want to use the information they identify.