Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › GraphWOZ: Dialogue Management with Conversational Knowledge Graphs

Publication

GraphWOZ: Dialogue Management with Conversational Knowledge Graphs

Walker, Nicholas Thomas; Ultes, Stefan; Lison, Pierre (2022): GraphWOZ: Dialogue Management with Conversational Knowledge Graphs, in: Arxiv.org, S. 1–17, doi: 10.48550/arXiv.2211.12852.

Details

Faculty/Chair
Faculty/Professorship
Author
Walker, Nicholas Thomas
Lison, Pierre
Corporate Body
Cornell University
Conference
The 13th International Workshop on Spoken Dialogue Systems Technology, Los Angeles
Publisher Information
Arxiv.org
Year of publication
2022
Language
English
DOI
URL
Abstract

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 dialogues in which human participants interact with a robot acting as a receptionist. In contrast to most existing work on dialogue management, GraphWOZ relies on a dialogue state explicitly represented as a dynamic knowledge graph instead of a fixed set of slots. This graph is composed of a varying number of entities (such as individuals, places, events, utterances and mentions) and relations between them (such as persons being part of a group or attending an event). The graph is then regularly updated on the basis of new observations and system actions. GraphWOZ is released along with detailed manual annotations related to the user intents, system responses, and reference relations occurring in both user and system turns. Based on GraphWOZ, we present experimental results for two dialogue management tasks, namely conversational entity linking and response ranking. For conversational entity linking, we show how to connect utterance mentions to their corresponding entity in the knowledge graph with a neural model relying on a combination of both string and graph-based features. Response ranking is then performed by summarizing the relevant content of the graph into a text, which is concatenated with the dialogue history and employed as input to score possible responses to a given dialogue state.

GND Keywords
Dialogsystem
Wissensgraph
Keywords
Dialogue Management
Knowledge Graph
DDC Classification
004 Computer science
RVK Classification
ST 302
Peer Reviewed
yes
International Distribution
yes
Type
Conferenceobject
URI
Activation date
2023-05-05

Permalink: https://fis.uni-bamberg.de/handle/uniba/58420 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.