BiSparse-AAS: Bilinear Sparse Attention and Adaptive Spans Framework for Scalable and Efficient Text Summarization

TL;DR

BiSparse-AAS introduces a scalable, efficient text summarization framework combining sparse attention, adaptive spans, and bilinear attention to improve performance on long documents.

Contribution

It proposes a novel framework that integrates sparse attention, adaptive spans, and bilinear attention to enhance scalability and effectiveness in text summarization.

Findings

Achieves about 68.1% ROUGE on CNN/DailyMail

Outperforms state-of-the-art baselines

Maintains strong performance on multiple datasets

Abstract

Transformer-based architectures have advanced text summarization, yet their quadratic complexity limits scalability on long documents. This paper introduces BiSparse-AAS (Bilinear Sparse Attention with Adaptive Spans), a novel framework that combines sparse attention, adaptive spans, and bilinear attention to address these limitations. Sparse attention reduces computational costs by focusing on the most relevant parts of the input, while adaptive spans dynamically adjust the attention ranges. Bilinear attention complements both by modeling complex token interactions within this refined context. BiSparse-AAS consistently outperforms state-of-the-art baselines in both extractive and abstractive summarization tasks, achieving average ROUGE improvements of about 68.1% on CNN/DailyMail and 52.6% on XSum, while maintaining strong performance on OpenWebText and Gigaword datasets. By addressing efficiency, scalability, and long-sequence modeling, BiSparse-AAS provides a unified, practical solution for real-world text summarization applications.