Collaborative Concept Extraction from Documents

A group of individuals who share the same interest or a task, would proot from making use of the knowledge possessed by the group. It is then essential that such a body of knowledge, or \community knowledge", be captured in an eeective manner. This paper describes the notion of Concept Index, which aims to index important concepts described in a collection of documents belonging to a group, and provide user-friendly cross-references among them to aid concept-oriented document space navigation. Unlike approaches relying primarily on automatic concept extraction tools, the Concept Index relies on users in identifying important concepts by marking keywords and phrases that interest them. Once the concepts are extracted in this manner, they are then enhanced by automated tools and more importantly by users who inspect them. We argue that with an appropriate support for users provided by a system, this interactive process optimises the index generated, and enhances collaboration between the members of the group in managing acquired information, and furthermore, leads to by-products such as a set of community vocabulary that are essential to eecient organisational work. The copyright of this paper belongs to the paper's authors. Permission to copy without fee all or part of this material is granted provided that the copies are not made or distributed for direct commercial advantage.