Personalizing Hybrid-Based Dialogue Agents

Yuri Matveev (), Olesia Makhnytkina, Pavel Posokhov, Anton Matveev and Stepan Skrylnikov
Additional contact information
Yuri Matveev: Information Technologies and Programming Faculty, ITMO University, 197101 Saint Petersburg, Russia
Olesia Makhnytkina: Information Technologies and Programming Faculty, ITMO University, 197101 Saint Petersburg, Russia
Pavel Posokhov: Information Technologies and Programming Faculty, ITMO University, 197101 Saint Petersburg, Russia
Anton Matveev: Information Technologies and Programming Faculty, ITMO University, 197101 Saint Petersburg, Russia
Stepan Skrylnikov: Information Technologies and Programming Faculty, ITMO University, 197101 Saint Petersburg, Russia

Mathematics, 2022, vol. 10, issue 24, 1-17

Abstract: In this paper, we present a continuation of our work on the personification of dialogue agents. We expand upon the previously demonstrated models—the ranking and generative models—and propose new hybrid models. Because there is no single definitive way to build a hybrid model, we explore various architectures where the components adopt different roles, sequentially and in parallel. Applying the perplexity and BLEU performance metrics, we discover that the Retrieve and Refine and KG model—a modification of the Retrieve and Refine model where the ranking and generative components work in parallel and compete based on the proximity of the candidate found by the ranking model with a knowledge-grounded generation block—achieves the best performance, with values of 1.64 for perplexity and 0.231 for BLEU scores.

Keywords: personalized dialogue systems; hybrid models; retrieve models; refine models (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/24/4657/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/24/4657/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:24:p:4657-:d:997853

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().