[4M3-OS-14c] OS-14

[4M3-OS-14c-03] Aspect-Based Novel Summarization with Relational Extraction Using Large Language Model

〇Ryuhei Miyazto¹, Hsin-Tai Wu², Kei Harada¹, Kazushi Okamoto¹, Atsushi Shibata³, Koki Karube¹ (1. The University of Electro-Communications, 2. DOCOMO Innovations, Inc., 3. Advanced Institute of Industrial Technology)

Keywords:Aspect-Based Summarization, Large Language Model, Entity Extraction, Novel Summarization

Automatic document summarization is a technique that extracts important elements from an original document and condenses them into short sentences. In this research, we propose an aspect-based summarization method for novels that generates summaries focusing on specific aspects. Specifically, we utilize Large Language Model (LLM) to extract the relationships between characters and events within the text and identify the aspect of each part of the novel based on these relationships. Subsequently, we collect the parts corresponding to the target aspect and generate a summary sentence for each aspect. To evaluate the summaries, we compare the answer accuracy to question-answer (QA) pairs created from the set of sentences corresponding to each aspect, using both the original document and the generated summary as references. The results demonstrate that the proposed method can generate summaries that comprehensively reflect the target aspect, a capability that was difficult to achieve with conventional methods.