QontSum: On Contrasting Salient Content for Query-focused Summarization

TL;DR

QontSum introduces a contrastive learning-based method for query-focused summarization that improves relevance and efficiency, outperforming or matching state-of-the-art results with less computational cost and human-verified relevance improvements.

Contribution

The paper presents QontSum, a novel contrastive learning approach for QFS that enhances relevance and reduces computational costs without extensive pre-training.

Findings

Outperforms existing state-of-the-art on benchmark datasets

Achieves comparable performance with reduced computational cost

Human study shows improved relevance of summaries

Abstract

Query-focused summarization (QFS) is a challenging task in natural language processing that generates summaries to address specific queries. The broader field of Generative Information Retrieval (Gen-IR) aims to revolutionize information extraction from vast document corpora through generative approaches, encompassing Generative Document Retrieval (GDR) and Grounded Answer Retrieval (GAR). This paper highlights the role of QFS in Grounded Answer Generation (GAR), a key subdomain of Gen-IR that produces human-readable answers in direct correspondence with queries, grounded in relevant documents. In this study, we propose QontSum, a novel approach for QFS that leverages contrastive learning to help the model attend to the most relevant regions of the input document. We evaluate our approach on a couple of benchmark datasets for QFS and demonstrate that it either outperforms existing state-of-the-art or exhibits a comparable performance with considerably reduced computational cost through enhancements in the fine-tuning stage, rather than relying on large-scale pre-training experiments, which is the focus of current SOTA. Moreover, we conducted a human study and identified improvements in the relevance of generated summaries to the posed queries without compromising fluency. We further conduct an error analysis study to understand our model's limitations and propose avenues for future research.