JSAI2024

Presentation information

International Session

International Session » IS-1 Knowledge engineering

[2Q5-IS-1] Knowledge engineering

Wed. May 29, 2024 3:30 PM - 5:10 PM Room Q (Room 402)

Chair: Ryo Nishida (AIST)

4:30 PM - 4:50 PM

[2Q5-IS-1-04] Data-driven Analysis of Domain Specificity for Explainable Session-based Recommendation System

〇Kotaro Okazaki1, Tony Ribeiro2, Kuo-Yen Lo1, Jyunichi Sakuma4, Katsumi Inoue3 (1. Sonar Inc., 2. Univ. Nantes, 3. National Institute of Informatics, 4. Video Research Ltd.)

Keywords:XAI, Inductive Logic Programming, Session-based Recommendation, Attention-based Neural Network

When utilizing sophisticated AI platforms for managerial decisionmaking based on observed user logs, the explainability of predictive models becomes key to trust. This explainability is significantly enhanced by understanding the domain-specificity within the predictive space. Therefore, attempts to capture domain-specificity from the internal states of large-scale language models applied in real business contexts can aid in model improvement and in formulating problems based on contextual information. In this paper, we propose an algorithmic framework that uses methods of inductive logic programming to extract logic rules directly from the sequence data logs and learned internal states of various session-based recommendation systems.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password