Jacques Chauché

Integrating Knowledge-based Hypertext and Database for Task-oriented Access to Documents

Dealing with huge technical document bases is a very hot topic for high technology industry. We focus on a full integration of database, knowledge-based system and hypertext techniques to provide task-oriented-access to documents. An external semantic-driven structure is mapped onto documents owing to knowledge based hypertext techniques. A database is used to keep the elements describing this structure and to help access documents. The overall structure organization is specified by a task model. A hypertext-like interface to the document base is used to navigate within the task-organized information space. Links dynamically result from complex computed relationships handled by the knowledge representation system between concepts and from the concepts anchorage into the text. A medium scale prototype for a real document base about nuclear engineering has been developed. The paper describes the principle of integrating the three techniques and discusses the implementation.

How to combine text-mining methods to validate induced verb-object relations?

This paper describes methods using Natural Language Processing approaches to extract and validate induced syntactic relations (here restricted to the Verb-Object relation). These methods use a syntactic parser and a semantic closeness measure to extract such relations. Then, their validation is based on two different techniques: A Web Validation system on one part, then a Semantic-Vectorbased approach, and finally different combinations of both techniques in order to rank induced Verb-Object relations. The Semantic Vector approach is a Roget-based method which computes a syntactic relation as a vector. Web Validation uses a search engine to determine the relevance of a syntactic relation according to its popularity. An experimental protocol is set up to judge automatically the relevance of the sorted induced relations. We finally apply our approach on a French corpus of news by using ROC Curves to evaluate the results.

A Hybrid Approach to Validate Induced Syntactic Relations

We propose in this paper to use NLP approaches to extract and validate induced syntactic relations (Verb-Object). We employ syntactic parser and a semantic proximity measure to extract them. Then, we focus on a Web Validation system, a Semantic-Vector-based approach, and finally we propose approaches to combine both in order to rank induced syntactic relations. The Semantic Vectors approach is a Roget-based method which computes a syntactic relation as a vector. Web Validation uses a search engine to determine the relevance of a syntactic relation. The systems combine Web Validation approach and Semantic Vectors technique. We apply our approaches on corpus of news, using ROC curves to evaluate the results.