Dialogue-Based Multi-Dimensional Relationship Extraction from Novels

TL;DR

This paper presents a novel LLM-based approach for extracting multi-dimensional character relationships from novels, addressing complex implicit expressions and constructing a Chinese novel dataset, thereby improving accuracy in relationship extraction.

Contribution

Introduces a relation extraction method leveraging relationship dimension separation, dialogue data, and contextual learning, along with a new Chinese novel dataset for improved performance.

Findings

Outperforms traditional baselines in multiple metrics

Enhances understanding of implicit relationships in complex contexts

Successfully constructs character relationship networks in novels

Abstract

Relation extraction is a crucial task in natural language processing, with broad applications in knowledge graph construction and literary analysis. However, the complex context and implicit expressions in novel texts pose significant challenges for automatic character relationship extraction. This study focuses on relation extraction in the novel domain and proposes a method based on Large Language Models (LLMs). By incorporating relationship dimension separation, dialogue data construction, and contextual learning strategies, the proposed method enhances extraction performance. Leveraging dialogue structure information, it improves the model's ability to understand implicit relationships and demonstrates strong adaptability in complex contexts. Additionally, we construct a high-quality Chinese novel relation extraction dataset to address the lack of labeled resources and support future research. Experimental results show that our method outperforms traditional baselines across multiple evaluation metrics and successfully facilitates the automated construction of character relationship networks in novels.