Dialogue-Based Multi-Dimensional Relationship Extraction from Novels

2025-07-07

AI Summary

Character relationship extraction in novels is challenging due to the high implicitness of relational semantics and complex contextual dependencies. To address this, we propose a relation-dimension separation strategy coupled with a dialogue-structure-aware data construction methodology, integrating large language models (LLMs), in-context learning, and dialogue-aware semantic modeling to enhance implicit relationship understanding. We introduce the first high-quality, manually annotated Chinese novel dataset for multidimensional character relationships—comprising character pairs, fine-grained relation types, relational strength scores, and context-based evidence spans. Our approach achieves significant improvements over conventional baselines across multiple evaluation metrics (e.g., F1, precision, recall). It enables automated, fine-grained character relationship network construction with strong generalizability, demonstrating practical applicability in literary analysis, knowledge graph construction, and downstream NLP tasks.

Technology Category

• Natural Language Processing: Information Extraction
• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Statistical Relational/Logic Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• Extracting multi-dimensional relationships from novel dialogues
• Addressing implicit expressions in complex novel contexts
• Overcoming lack of labeled datasets for novel relation extraction

Innovation

• Uses Large Language Models for novel relation extraction
• Incorporates dialogue data and contextual learning
• Constructs Chinese novel dataset for relation extraction