Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Hana, Ong, Kai Tzu-iunn, Kim, Seoyeon, Lee, Dongha, Yeo, Jinyoung
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916120916656128
author Kim, Hana
Ong, Kai Tzu-iunn
Kim, Seoyeon
Lee, Dongha
Yeo, Jinyoung
author_facet Kim, Hana
Ong, Kai Tzu-iunn
Kim, Seoyeon
Lee, Dongha
Yeo, Jinyoung
contents Memorizing and utilizing speakers' personas is a common practice for response generation in long-term conversations. Yet, human-authored datasets often provide uninformative persona sentences that hinder response quality. This paper presents a novel framework that leverages commonsense-based persona expansion to address such issues in long-term conversation. While prior work focuses on not producing personas that contradict others, we focus on transforming contradictory personas into sentences that contain rich speaker information, by refining them based on their contextual backgrounds with designed strategies. As the pioneer of persona expansion in multi-session settings, our framework facilitates better response generation via human-like persona refinement. The supplementary video of our work is available at https://caffeine-15bbf.web.app/.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14215
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement
Kim, Hana
Ong, Kai Tzu-iunn
Kim, Seoyeon
Lee, Dongha
Yeo, Jinyoung
Computation and Language
Artificial Intelligence
Memorizing and utilizing speakers' personas is a common practice for response generation in long-term conversations. Yet, human-authored datasets often provide uninformative persona sentences that hinder response quality. This paper presents a novel framework that leverages commonsense-based persona expansion to address such issues in long-term conversation. While prior work focuses on not producing personas that contradict others, we focus on transforming contradictory personas into sentences that contain rich speaker information, by refining them based on their contextual backgrounds with designed strategies. As the pioneer of persona expansion in multi-session settings, our framework facilitates better response generation via human-like persona refinement. The supplementary video of our work is available at https://caffeine-15bbf.web.app/.
title Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2401.14215