Zum Inhalt springen

Nur-Lesen-Fassung: Das Forschungsinformationssystem (FIS) ist aus Sicherheitsgründen vorübergehend durch diese Nur-Lesen-Fassung ersetzt. Alle öffentlichen Inhalte und Volltexte sind weiterhin abrufbar; Anmeldung, Bearbeitung, Einreichung und Statistiken stehen nicht zur Verfügung. Bei Fragen: fis@uni-bamberg.de

Start › Publikationen › System-Initiated Transitions from Chit-Chat to Task-Oriented Dialogues with Transition Info Extractor and Transition Sentence Generator

Publikation

System-Initiated Transitions from Chit-Chat to Task-Oriented Dialogues with Transition Info Extractor and Transition Sentence Generator

Liu, Ye; Ultes, Stefan; Minker, Wolfgang; u. a. (2023): System-Initiated Transitions from Chit-Chat to Task-Oriented Dialogues with Transition Info Extractor and Transition Sentence Generator, in: Proceedings of the 16th International Natural Language Generation Conference, Prague, Czechia: Association for Computational Linguistics, S. 279–292.

Details

Fakultät/Lehrstuhl
Autorin(nen)/Autor(en)
Liu, Ye
Minker, Wolfgang
Maier, Wolfgang
Titel des Sammelwerks
Proceedings of the 16th International Natural Language Generation Conference
Konferenz
16th International Natural Language Generation Conference 2023, Prague, Czechia
Verlagsangabe
Association for Computational Linguistics : Prague, Czechia
Erscheinungsjahr
2023
Sprache(n)
Englisch
URL
Abstract

In this work, we study dialogue scenarios that start from chit-chat but eventually switch to task-related services, and investigate how a unified dialogue model, which can engage in both chit-chat and task-oriented dialogues, takes the initiative during the dialogue mode transition from chit-chat to task-oriented in a coherent and cooperative manner. We firstly build a transition info extractor (TIE) that keeps track of the preceding chit-chat interaction and detects the potential user intention to switch to a task-oriented service. Meanwhile, in the unified model, a transition sentence generator (TSG) is extended through efficient Adapter tuning and transition prompt learning. When the TIE successfully finds task-related information from the preceding chit-chat, such as a transition domain (“train” in Figure fig: system-initiated transition from chit-chat to task-oriented.), then the TSG is activated automatically in the unified model to initiate this transition by generating a transition sentence under the guidance of transition information extracted by TIE. The experimental results show promising performance regarding the proactive transitions. We achieve an additional large improvement on TIE model by utilizing Conditional Random Fields (CRF). The TSG can flexibly generate transition sentences while maintaining the unified capabilities of normal chit-chat and task-oriented response generation.

GND-Schlagwort(e)
Dialogsystem
Mensch-Maschine-Kommunikation
Freie Schlagwort(e)
System-Initiated Transitions
DDC-Klassifikation
004 Computer science
RVK-Klassifikation
ST 306
Peer Reviewed
ja
Internationale Verbreitung
ja
Open-Access-Zeitschrift
ja
Dokumenttyp
Konferenzveröffentlichung
URI
Datum der Freischaltung
05.10.2023

Permalink: https://fis.uni-bamberg.de/handle/uniba/91203 · Daten als JSON · Zitieren: BibTeX · RIS

Datenstand: 15.11.2026

Eingeschränkter Lesezugriff: Anmeldung, Bearbeitung und Einreichung sind vorübergehend deaktiviert.