QontSum: On Contrasting Salient Content for Query-focused Summarization
Preprint
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.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- QSG Transformer2022
- Domain Adaptation with Pre-trained Transformers for Query Focused Abstractive Text SummarizationComputational Linguistics, 2022
- Document Summarization with Latent QueriesTransactions of the Association for Computational Linguistics, 2022
- Decision-Focused Summarization2021
- SimCSE: Simple Contrastive Learning of Sentence Embeddings2021
- Coarse-to-Fine Query Focused Multi-Document Summarization2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- Learning visual similarity for product design with convolutional neural networksACM Transactions on Graphics, 2015
- Towards Efficient Similar Sentences ExtractionLecture Notes in Computer Science, 2012
- LexRank: Graph-based Lexical Centrality as Salience in Text SummarizationJournal of Artificial Intelligence Research, 2004