EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Knowledge-Grounded Task-Oriented Dialogue System with Hierarchical Structure for Enhancing Knowledge Selection

Hayoung Lee, Okran Jeong

Sensors · 2023

DOI: 10.3390/s23020685 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Hayoung Lee und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing, Gachon University, 1342 Sujeong-gu, Seongnam-si 13120, Gyeonggi-do, Republic of Korea. Hauptthemen laut MEDLINE: Language, Communication. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Gachon University research fund, Basic Science Research Program through the NRF (National Research Foundation of Korea), MSIT (Ministry of Science and Author ICT).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

For a task-oriented dialogue system to provide appropriate answers to and services for users’ questions, it is necessary for it to be able to utilize knowledge related to the topic of the conversation. Therefore, the system should be able to select the most appropriate knowledge snippet from the knowledge base, where external unstructured knowledge is used to respond to user requests that cannot be solved by the internal knowledge addressed by the database or application programming interface. Therefore, this paper constructs a three-step knowledge-grounded task-oriented dialogue system with knowledge-seeking-turn detection, knowledge selection, and knowledge-grounded generation. In particular, we propose a hierarchical structure of domain-classification, entity-extraction, and snippet-ranking tasks by subdividing the knowledge selection step. Each task is performed through the pre-trained language model with advanced techniques to finally determine the knowledge snippet to be used to generate a response. Furthermore, the domain and entity information obtained because of the previous task is used as knowledge to reduce the search range of candidates, thereby improving the performance and efficiency of knowledge selection and proving it through experiments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LanguageCommunicationKnowledge BasesNatural Language ProcessingSoftware

Stichwörter der Autor:innen

classificationconversational AIknowledge selectionknowledge-grounded task-oriented dialogue systemnamed entity recognitionnegative samplingsnippet ranking

Autor:innen und Institutionen

  • School of Computing, Gachon University, 1342 Sujeong-gu, Seongnam-si 13120, Gyeonggi-do, Republic of Korea.

Förderung

  • Gachon University research fund
  • Basic Science Research Program through the NRF (National Research Foundation of Korea)
  • MSIT (Ministry of Science and Author ICT)

Zitieren

APA

Lee, H., & Jeong, O. (2023). A Knowledge-Grounded Task-Oriented Dialogue System with Hierarchical Structure for Enhancing Knowledge Selection. Sensors. https://doi.org/10.3390/s23020685

Vancouver

Lee H, Jeong O. A Knowledge-Grounded Task-Oriented Dialogue System with Hierarchical Structure for Enhancing Knowledge Selection. Sensors. 2023. doi:10.3390/s23020685

BibTeX
@article{Lee2023,
  author = {Lee, Hayoung and Jeong, Okran},
  title = {A Knowledge-Grounded Task-Oriented Dialogue System with Hierarchical Structure for Enhancing Knowledge Selection},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23020685}
}
Kostenlos starten →