K-Act2Emo: Korean Commonsense Knowledge Graph for Indirect Emotional Expression

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kim, Kyuhee, Lee, Surin, Lee, Sangah
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910379248975872
author Kim, Kyuhee
Lee, Surin
Lee, Sangah
author_facet Kim, Kyuhee
Lee, Surin
Lee, Sangah
contents In many literary texts, emotions are indirectly conveyed through descriptions of actions, facial expressions, and appearances, necessitating emotion inference for narrative understanding. In this paper, we introduce K-Act2Emo, a Korean commonsense knowledge graph (CSKG) comprising 1,900 indirect emotional expressions and the emotions inferable from them. We categorize reasoning types into inferences in positive situations, inferences in negative situations, and inferences when expressions do not serve as emotional cues. Unlike existing CSKGs, K-Act2Emo specializes in emotional contexts, and experimental results validate its effectiveness for training emotion inference models. Significantly, the BART-based knowledge model fine-tuned with K-Act2Emo outperforms various existing Korean large language models, achieving performance levels comparable to GPT-4 Turbo.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14253
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle K-Act2Emo: Korean Commonsense Knowledge Graph for Indirect Emotional Expression
Kim, Kyuhee
Lee, Surin
Lee, Sangah
Computation and Language
In many literary texts, emotions are indirectly conveyed through descriptions of actions, facial expressions, and appearances, necessitating emotion inference for narrative understanding. In this paper, we introduce K-Act2Emo, a Korean commonsense knowledge graph (CSKG) comprising 1,900 indirect emotional expressions and the emotions inferable from them. We categorize reasoning types into inferences in positive situations, inferences in negative situations, and inferences when expressions do not serve as emotional cues. Unlike existing CSKGs, K-Act2Emo specializes in emotional contexts, and experimental results validate its effectiveness for training emotion inference models. Significantly, the BART-based knowledge model fine-tuned with K-Act2Emo outperforms various existing Korean large language models, achieving performance levels comparable to GPT-4 Turbo.
title K-Act2Emo: Korean Commonsense Knowledge Graph for Indirect Emotional Expression
topic Computation and Language
url https://arxiv.org/abs/2403.14253