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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: DeLucia, Alexandra, Zhao, Mengjie, Maeda, Yoshinori, Yoda, Makoto, Yamada, Keiichi, Wakaki, Hiromi
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914639848144896
author DeLucia, Alexandra
Zhao, Mengjie
Maeda, Yoshinori
Yoda, Makoto
Yamada, Keiichi
Wakaki, Hiromi
author_facet DeLucia, Alexandra
Zhao, Mengjie
Maeda, Yoshinori
Yoda, Makoto
Yamada, Keiichi
Wakaki, Hiromi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_06742
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domain
DeLucia, Alexandra
Zhao, Mengjie
Maeda, Yoshinori
Yoda, Makoto
Yamada, Keiichi
Wakaki, Hiromi
Computation and Language
Artificial Intelligence
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.
title Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domain
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2401.06742