Dialogue You Can Trust: Human and AI Perspectives on Generated Conversations

no code implementations • 3 Sep 2024 • Ike Ebubechukwu, Johane Takeuchi, Antonello Ceravola, Frank Joublin

This study explores the comparative performance of human and AI assessments across a range of dialogue scenarios, focusing on seven key performance indicators (KPIs): Coherence, Innovation, Concreteness, Goal Contribution, Commonsense Contradiction, Incorrect Fact, and Redundancy.

Dialogue Evaluation

Utilization of domain knowledge to improve POMDP belief estimation

no code implementations • 17 Feb 2023 • Tung Nguyen, Johane Takeuchi

The partially observable Markov decision process (POMDP) framework is a common approach for decision making under uncertainty.

Decision Making Decision Making Under Uncertainty

Nonparametric Bayesian Models for Spoken Language Understanding

no code implementations • EMNLP 2016 • Kei Wakabayashi, Johane Takeuchi, Kotaro Funakoshi, Mikio Nakano

Slot Filling Spoken Language Understanding