AgreeSum: Agreement-Oriented Multi-Document Summarization

By Richard Yuanzhe Pang, Á. Lelkes, Vinh Q. Tran, Cong Yu. 2021

18 citations recorded by the source corpus.

We aim to renew interest in a particular multi-document summarization (MDS) task which we call AgreeSum: agreement-oriented multi-document summarization. Given a cluster of articles, the goal is to provide abstractive summaries that represent information common and faithful to all input articles. Given the lack of existing datasets, we create a dataset for AgreeSum, and provide annotations on article-summary entailment relations for a subset of the clusters in the dataset. We aim to create strong baselines for the task by applying the top-performing pretrained single-document summarization model PEGASUS onto AgreeSum, leveraging both annotated clusters by supervised losses, and unannotated clusters by T5-based entailment-related and language-related losses. Compared to other baselines, both automatic evaluation and human evaluation show better article-summary and cluster-summary entailment in generated summaries. On a separate note, we hope that our article-summary entailment annotations contribute to the community's effort in improving abstractive summarization faithfulness.

Subfields: Artificial Intelligence, Summarization

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Multi-document Summarization via Deep Learning Techniques: A Survey (2020, methodology): “BART [88], GPT-2 [133], and T5 [134] are pre-trained language models that can be used for language generation and they have been applied for MDS tasks [2, 122, 147].”
SQuALITY: Building a Long-Document Summarization Dataset the Hard Way (2022, methodology): “We assign stories to splits to be consistent with the QuALITY dataset (Pang et al., 2021b), so stories that appear in both datasets are assigned to the same split.”