ITCLLGJan 22, 2025

A Rate-Distortion Framework for Summarization

arXiv:2501.13100v22 citationsh-index: 6ISIT
AI Analysis

This work addresses the challenge of establishing theoretical performance limits for text summarization, which is incremental as it applies existing rate-distortion concepts to a new domain.

The paper tackles the problem of text summarization by introducing an information-theoretic framework that defines a summarizer rate-distortion function, providing a fundamental lower bound on performance, and empirically confirms this by comparing it with practical summarizers.

This paper introduces an information-theoretic framework for text summarization. We define the summarizer rate-distortion function and show that it provides a fundamental lower bound on summarizer performance. We describe an iterative procedure, similar to Blahut-Arimoto algorithm, for computing this function. To handle real-world text datasets, we also propose a practical method that can calculate the summarizer rate-distortion function with limited data. Finally, we empirically confirm our theoretical results by comparing the summarizer rate-distortion function with the performances of different summarizers used in practice.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes