Defense
My thesis entitled "Design of a natural language processing chain for an assistant conversational agent" has been defended on Tuesday June 29th 2010 at 2:00pm in the conference room of the LIMSI-CNRS, in front of the following jury members:
- Guy Lapalme, Professor at Montreal University, RALI (reviewer)
- Catherine Pelachaud, Research director at LTCI Télécom ParisTech (president)
- Sylvie Pesty, Professor at University Pierre Mendès-France, LIG (reviewer)
- Jean-Paul Sansonnet, Research director at LIMSI-CNRS (thesis supervisor)
- Anne Vilnat, Professor at University Paris-Sud 11, LIMSI-CNRS (examiner)
Summary
With the increasing number of novice users of computer applications, the need for efficient assistance has become critical. To supply the need, we suggest using an Assistant Conversational Agent (ACA), an interface allowing the use of natural language (used spontaneously when a problem arises) and providing a reassuring presence to the users.
A preliminary study details the constitution (combining collection and the use of thesauri) of a corpus of requests, which need is justified. This corpus of 11,626 requests is compared with others, and we show that it covers the studied domain of assistance and moreover, contains requests regarding controlling of the application and chatting with the agent.
This corpus provides a sound foundation for the conception of a syntactico-semantic analyzer of natural language requests, using a set of semantic keys, a set of analysis rules and a set of transformation rules. In output, requests are expressed in a formal language (DAFT) for which we provide the syntax and the semantics.
The analyzer is evaluated by comparing a manual annotation and the requests automatically produced, and we consider the use of some supervised machine learning approaches in order to identify conversational activities.
The methodology followed is validated through the integration of an ACA into an existing Web application for cooperative music prototyping.
Finally, we describe the required architecture for the rational agent in charge of defining the reactions based on the formal requests expressed in DAFT and on the model of the assisted application, emphasizing the need for a cognitive model.