paper-with-me

Papers

Action State Update Approach to Dialogue Management

2020-11-09 · Svetlana Stoyanchev, Simon Keizer, Rama Doddipatla

Utterance interpretation is one of the main functions of a dialogue manager, which is the key component of a dialogue system. We propose the action state update approach (ASU) for utterance interpretation, featuring a statistically trained binary classifier used to detect dialogue state update actions in the text of a user utterance. Our goal is to interpret referring expressions in user input without a domain-specific natural language understanding component. For training the model, we use active learning to automatically select simulated training examples. With both user-simulated and interactive human evaluations, we show that the ASU approach successfully interprets user utterances in a dialogue system, including those with referring expressions.

📄 PDF Abstract BibTeX arXiv:2011.04637

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningDialogue ManagementManagementNatural Language Understanding

Methods 이 논문이 사용한 방법론

ASU 2023

Similar Papers 제목 키워드 기반

Memory-augmented Dialogue Management for Task-oriented Dialogue Systems

2018-05-01 · Zheng Zhang, Minlie Huang, Zhongzhou Zhao, Feng Ji 외

Dialogue management (DM) decides the next action of a dialogue system according to the current dialogue state, and thus plays a central role in task-oriented dialogue systems. Since dialogue management requires to have a…

Dialogue ManagementManagementTask-Oriented Dialogue Systems

GraphWOZ: Dialogue Management with Conversational Knowledge Graphs

2022-11-23 · Nicholas Thomas Walker, Stefan Ultes, Pierre Lison

We present a new approach to dialogue management using conversational knowledge graphs as core representation of the dialogue state. To this end, we introduce a new dataset, GraphWOZ, which comprises Wizard-of-Oz dialogu…

Dialogue ManagementEntity LinkingKnowledge GraphsManagement

Cascaded LSTMs based Deep Reinforcement Learning for Goal-driven Dialogue

2019-10-31 · Yue Ma, Xiaojie Wang, Zhenjiang Dong, Hong Chen

This paper proposes a deep neural network model for joint modeling Natural Language Understanding (NLU) and Dialogue Management (DM) in goal-driven dialogue systems. There are three parts in this model. A Long Short-Term…

Deep Reinforcement LearningDialogue ManagementManagementNatural Language Understanding+3

Deep Reinforcement Learning for On-line Dialogue State Tracking

2020-09-22 · Zhi Chen, Lu Chen, Xiang Zhou, Kai Yu

Dialogue state tracking (DST) is a crucial module in dialogue management. It is usually cast as a supervised training problem, which is not convenient for on-line optimization. In this paper, a novel companion teaching b…

Deep Reinforcement LearningDialogue ManagementDialogue State TrackingManagement+4

Latent-IM: Latent Interaction Management for Speech LLMs

2026-07-29 · Adar Avsian, Atahan Dokme, Tony Woo, Larry Heck arxiv

Classical spoken dialogue systems often separated dialogue management from response realization: a policy selected the next dialogue action, and a generation component expressed that action. As dialogue systems shift tow…