Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domain

While valuable datasets such as PersonaChat provide a foundation for training persona-grounded dialogue agents, they lack diversity in conversational and narrative settings, primarily existing in the "real" world. To develop dialogue agents with unique personas, models are trained to conve...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-01
Main Authors: DeLucia, Alexandra, Zhao, Mengjie, Maeda, Yoshinori, Yoda, Makoto, Yamada, Keiichi, Wakaki, Hiromi
Format: Article
Language:English
Subjects:
Annotations
Datasets
Inference
Natural language
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:While valuable datasets such as PersonaChat provide a foundation for training persona-grounded dialogue agents, they lack diversity in conversational and narrative settings, primarily existing in the "real" world. To develop dialogue agents with unique personas, models are trained to converse given a specific persona, but hand-crafting these persona can be time-consuming, thus methods exist to automatically extract persona information from existing character-specific dialogue. However, these persona-extraction models are also trained on datasets derived from PersonaChat and struggle to provide high-quality persona information from conversational settings that do not take place in the real world, such as the fantasy-focused dataset, LIGHT. Creating new data to train models on a specific setting is human-intensive, thus prohibitively expensive. To address both these issues, we introduce a natural language inference method for post-hoc adapting a trained persona extraction model to a new setting. We draw inspiration from the literature of dialog natural language inference (NLI), and devise NLI-reranking methods to extract structured persona information from dialogue. Compared to existing persona extraction models, our method returns higher-quality extracted persona and requires less human annotation.
ISSN:2331-8422