Integrating Conversational Entities and Dialogue Histories with Knowledge Graphs and Generative AI

Graham Wilcock; Kristiina Jokinen

Integrating Conversational Entities and Dialogue Histories with Knowledge Graphs and Generative AI

Forskningsoutput: Kapitel i bok/rapport/konferenshandling › Konferensbidrag › Vetenskaplig › Peer review

Sammanfattning

Existing methods for storing dialogue history and for tracking mentioned entities in spoken dialogues usually handle these tasks separately. Recent advances in knowledge graphs and generative AI make it possible to integrate them in a framework with a uniform representation for dialogue management. This may help to build more natural and grounded dialogue models that can reduce misunderstanding and lead to more reliable dialogue-based interactions with AI agents. The paper describes ongoing work on this approach.

Originalspråk	engelska
Titel på värdpublikation	Proceedings Of The 15th International Workshop On Spoken Dialogue Systems Technology
Redaktörer	Maria Ines Torres, Yuki Matsuda, Zoraida Callejas, Arantza DelPozo, Luis Fernando D'Haro
Antal sidor	9
Utgivningsort	Stroudsburg
Förlag	ACL
Utgivningsdatum	2025
Sidor	290-298
ISBN (elektroniskt)	979-8-89176-248-0
Status	Publicerad - 2025
MoE-publikationstyp	A4 Artikel i en konferenspublikation
Evenemang	International Workshop on Spoken Dialogue Systems Technology - Bilbao, Spanien Varaktighet: 27 maj 2025 → 30 maj 2025 Konferensnummer: 15

Vetenskapsgrenar

6121 Språkvetenskaper

Åtkomst av dokument

2025.iwsds-1.31Slutlig publicerad version, 822 KBLicens: CC BY

Citera det här

@inproceedings{2a6715b5be4d4bb693e31d18030f8bc6,

title = "Integrating Conversational Entities and Dialogue Histories with Knowledge Graphs and Generative AI",

abstract = "Existing methods for storing dialogue history and for tracking mentioned entities in spoken dialogues usually handle these tasks separately. Recent advances in knowledge graphs and generative AI make it possible to integrate them in a framework with a uniform representation for dialogue management. This may help to build more natural and grounded dialogue models that can reduce misunderstanding and lead to more reliable dialogue-based interactions with AI agents. The paper describes ongoing work on this approach.",

keywords = "6121 Languages",

author = "Graham Wilcock and Kristiina Jokinen",

year = "2025",

language = "English",

pages = "290--298",

editor = "Torres, \{Maria Ines\} and Yuki Matsuda and Zoraida Callejas and Arantza DelPozo and D'Haro, \{Luis Fernando\}",

booktitle = "Proceedings Of The 15th International Workshop On Spoken Dialogue Systems Technology",

publisher = "ACL",

address = "United States",

note = " International Workshop on Spoken Dialogue Systems Technology, IWSDS ; Conference date: 27-05-2025 Through 30-05-2025",

}

Wilcock, G & Jokinen, K 2025, Integrating Conversational Entities and Dialogue Histories with Knowledge Graphs and Generative AI. i MI Torres, Y Matsuda, Z Callejas, A DelPozo & LF D'Haro (red), Proceedings Of The 15th International Workshop On Spoken Dialogue Systems Technology. ACL, Stroudsburg, s. 290-298, International Workshop on Spoken Dialogue Systems Technology, Bilbao, Spanien, 27/05/2025.

Integrating Conversational Entities and Dialogue Histories with Knowledge Graphs and Generative AI. / Wilcock, Graham ; Jokinen, Kristiina.
Proceedings Of The 15th International Workshop On Spoken Dialogue Systems Technology. red. / Maria Ines Torres; Yuki Matsuda; Zoraida Callejas; Arantza DelPozo; Luis Fernando D'Haro. Stroudsburg: ACL, 2025. s. 290-298.

Forskningsoutput: Kapitel i bok/rapport/konferenshandling › Konferensbidrag › Vetenskaplig › Peer review

TY - GEN

T1 - Integrating Conversational Entities and Dialogue Histories with Knowledge Graphs and Generative AI

AU - Wilcock, Graham

AU - Jokinen, Kristiina

N1 - Conference code: 15

PY - 2025

Y1 - 2025

N2 - Existing methods for storing dialogue history and for tracking mentioned entities in spoken dialogues usually handle these tasks separately. Recent advances in knowledge graphs and generative AI make it possible to integrate them in a framework with a uniform representation for dialogue management. This may help to build more natural and grounded dialogue models that can reduce misunderstanding and lead to more reliable dialogue-based interactions with AI agents. The paper describes ongoing work on this approach.

AB - Existing methods for storing dialogue history and for tracking mentioned entities in spoken dialogues usually handle these tasks separately. Recent advances in knowledge graphs and generative AI make it possible to integrate them in a framework with a uniform representation for dialogue management. This may help to build more natural and grounded dialogue models that can reduce misunderstanding and lead to more reliable dialogue-based interactions with AI agents. The paper describes ongoing work on this approach.

KW - 6121 Languages

M3 - Conference contribution

SP - 290

EP - 298

BT - Proceedings Of The 15th International Workshop On Spoken Dialogue Systems Technology

A2 - Torres, Maria Ines

A2 - Matsuda, Yuki

A2 - Callejas, Zoraida

A2 - DelPozo, Arantza

A2 - D'Haro, Luis Fernando

PB - ACL

CY - Stroudsburg

T2 - International Workshop on Spoken Dialogue Systems Technology

Y2 - 27 May 2025 through 30 May 2025

ER -