paper-with-me

홈 › Papers

Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles

2020-10-06 · Findings of the Association for Computational Linguistics 2020 · Carel van Niekerk, Michael Heck, Christian Geishauser, Hsien-Chin Lin, Nurul Lubis, Marco Moresi, Milica Gašić

The ability to accurately track what happens during a conversation is essential for the performance of a dialogue system. Current state-of-the-art multi-domain dialogue state trackers achieve just over 55% accuracy on the current go-to benchmark, which means that in almost every second dialogue turn they place full confidence in an incorrect dialogue state. Belief trackers, on the other hand, maintain a distribution over possible dialogue states. However, they lack in performance compared to dialogue state trackers, and do not produce well calibrated distributions. In this work we present state-of-the-art performance in calibration for multi-domain dialogue belief trackers using a calibrated ensemble of models. Our resulting dialogue belief tracker also outperforms previous dialogue belief tracking models in terms of accuracy.

📄 PDF Abstract BibTeX arXiv:2010.02586

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Proactive Knowledge Inquiry in Doctor-Patient Dialogue: Stateful Extraction, Belief Updating, and Path-Aware Action Planning

2026-03-18 · Zhenhai Pan, Yan Liu, Jia You arxiv

Most automated electronic medical record (EMR) pipelines remain output-oriented: they transcribe, extract, and summarize after the consultation, but they do not explicitly model what is already known, what is still missi…

BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts

2025-12-31 · Hengli Li, Zhaoxin Yu, Qi Shen, Chenxi Li 외 arxiv

Strategic dialogue requires agents to execute distinct dialogue acts, for which belief estimation is essential. While prior work often estimates beliefs accurately, it lacks a principled mechanism to use those beliefs du…

Beyond knowing that: a new generation of epistemic logics

2016-05-06 · Yanjing Wang

Epistemic logic has become a major field of philosophical logic ever since the groundbreaking work by Hintikka (1962). Despite its various successful applications in theoretical computer science, AI, and game theory, the…

Survey

A Method for Using Belief Networks as Influence Diagrams

2013-03-27 · Gregory F. Cooper

This paper demonstrates a method for using belief-network algorithms to solve influence diagram problems. In particular, both exact and approximation belief-network algorithms may be applied to solve influence-diagram pr…

Distilling Bayesian Belief States into Language Models for Auditable Negotiation

2026-05-06 · Zongqi Cui, Baihan Lin arxiv

Negotiation agents must infer what their counterpart values, update those beliefs over dialogue turns, and choose actions under uncertainty. End-to-end large language models (LLMs) can imitate negotiation dialogue, but t…

Decision Making