Early Stage Researcher at WUT
HeZhang is interested in computational argumentation in the aspect of social media. She has a background in Artificial intelligence. She likes to dig more about computer science applications in linguistic study.
Warsaw University of Technology (WUT)
Department of Philosophy and Ethics in Administration
Plac Politechniki 1
00-661 Warsaw, Poland
Connect
- he.zhang@pw.edu.pl
- +48-570112644
Follow
Customized interactive argumentation schemes for XAI
• Main Supervisor: Dr Katarzyna Budzynska, Politechnika Warszawska – Warsaw University of Technology (WUT) budzynska.argdiap@gmail.com
• PhD Co-Supervisor: Dr. Jose M. Alonso, Centro Singular de Investigación en Tecnoloxías Intelixentes (CiTIUS) – Universidade de Santiago de Compostela (USC)
• Inter-sectoral Secondment Supervisor: Mr. R. Diñeiro, Accenture Technology
PhD research topic
Objectives:
To define, design, develop and validate a new methodology for argumentation schemes tailored for planning and handling the discourse history in interactive conversational agents aimed at explaining AI in NL. The customization will be achieved through the creation of a profile of the user and then adaptation of argumentation to match this profile. This will involve both the analysis and the representation of the use of argumentation in natural communication in the specific genre, and the application of Budzynska’s previous pioneering work on ethotic strategies in NL, i.e., on the communicative behaviour dependent on the character of the speaker.
Main Challenges:
– modelling context and common ground;
– dealing with reference expressions;
– implicit knowledge and embedded testimony;
– empowering the conversational agent with credibility.
Use cases:
(1) explaining decision trees to non-expert users (Universidade de Santiago de Compostela- USC); and
(2) a real use case defined in an inter-sectoral secondment (Accenture).
Expected Results:
(1) Understanding of the state of the art in relevant aspects of argumentation theory and dialogue systems for XAI.
(2) Analysis SWOT of existing argumentation schemes and their extensions (including ethotic extensions) for conversational agents.
(3) Definition and implementation of a new protocol for handling profiles of users and the discourse history with explanation purposes.
(4) Validation of this protocol in two use cases.
