Abstractive Summarization of Large Document Collections Using GPT

2023/10/09 by Christopher G. Healey, Liu, Sengjie, Healey, Christopher G. · 1 citation
Computer Science · #Advanced Text Analysis Techniques #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #H.3.1 #I.2.7 #I.3.3 #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2310.05690

openalex publication_date 2023/10/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper proposes a method of abstractive summarization designed to scale to document collections instead of individual documents. Our approach applies a combination of semantic clustering, document size reduction within topic clusters, semantic chunking of a cluster's documents, GPT-based summarization and concatenation, and a combined sentiment and text visualization of each topic to support exploratory data analysis. Statistical comparison of our results to existing state-of-the-art systems BART, BRIO, PEGASUS, and MoCa using ROGUE summary scores showed statistically equivalent performance with BART and PEGASUS on the CNN/Daily Mail test dataset, and with BART on the Gigaword test dataset. This finding is promising since we view document collection summarization as more challenging than individual document summarization. We conclude with a discussion of how issues of scale are

Cited by

• Document Intelligence in the Era of Large Language Models: A Survey

Related

• Document-Level Abstractive Summarization
• Large-Scale Multi-Document Summarization with Information Extraction and Compression
• Markov-Enhanced Clustering for Long Document Summarization: Tackling the 'Lost in the Middle' Challenge with Large Language Models
• Abstractive Document Summarization without Parallel Data
• A Split-then-Join Approach to Abstractive Summarization for Very Long Documents in a Low Resource Setting