Text Summarization with Latent Queries

Abstract

The availability of large-scale datasets has driven the development of neural models that create summaries from single documents, for generic purposes. When using a summarization system, users often have specific intents with various language realizations, which, depending on the information need, can range from a single keyword to a long narrative composed of multiple questions. Existing summarization systems, however, often either fail to support or act robustly on this query focused summarization task. We introduce LAQSUM, the first unified text summarization system that learns Latent Queries from documents for abstractive summarization with any existing query forms. Under a deep generative framework, our system jointly optimizes a latent query model and a conditional language model, allowing users to plug-and-play queries of any type at test time. Despite learning from only generic summarization data and requiring no further optimization for downstream summarization tasks, our system robustly outperforms strong comparison systems across summarization benchmarks with different query types, document settings, and target domains.

Domain Adaptation with Pre-trained Transformers for Query-Focused Abstractive Text Summarization

“…The topic of query-focused abstractive summarization has remained underexplored for the multi-document scenario as well (Kulkarni et al 2020). More importantly, the currently available query focused multi-document abstractive summarization (MD-QFAS) datasets (e.g., DUC 2 2005, 2006, 2007) do not contain any labeled training data, that is, these datasets only provide test data (Baumel, Eyal, and Elhadad 2018;Goodwin, Savery, and Demner-Fushman 2020;Su et al 2020;Xu and Lapata 2021). To tackle the lack of training data for the MD-QFAS task, most previous work was based on various unsupervised approaches that could only generate extractive summaries (Wang et al 2008;Haghighi and Vanderwende 2009;Wan and Xiao 2009;Yao, Wan, and Xiao 2015;Zhong et al 2015;Wan and Zhang 2014;Ma, Deng, and Yang 2016;Feigenblat et al 2017).…”

Can Large Language Models Fix Data Annotation Errors? An Empirical Study Using Debatepedia for Query-Focused Text Summarization

“…Query-focused text summarization is a specific type of summarization that generates a summary of the given text that is focused on answering a specific question (Laskar et al, 2020c) or addressing a particular topic, rather than providing a general overview of the text. (Baumel et al, 2018;Goodwin et al, 2020;Su et al, 2020;Xu and Lapata, 2021;Laskar et al, 2020aLaskar et al, ,b, 2022.…”

Query-Focused Extractive Summarisation for Finding Ideal Answers to Biomedical and COVID-19 Questions

“…Supervised approaches to query-focused summarisation have the inherent problem of the paucity of annotated data. This problem has been highlighted, for example, by [1], and the biomedical domain is no exception. The BioASQ Challenge provides annotated data for multiple tasks, including question answering [2].…”

“…This paper describes our contribution to the BioASQ Synergy task and phase B of the BioASQ9b challenge. 1 For the BioASQ Synergy task, we use a system that has been trained on the BioASQ8b training data, whereas for phase B of the BioASQ9b challenge we explore the use of Transformer architectures. In particular, we integrate BERT variants and fine-tune them with the BioASQ9b training data.…”