AgreeSum: Agreement-Oriented Multi-Document Summarization
This work addresses the need for faithful and common information summaries in multi-document settings, though it is incremental as it builds on existing models and datasets.
The authors tackled the problem of agreement-oriented multi-document summarization (AgreeSum) by creating a new dataset and applying the PEGASUS model with supervised and entailment-related losses, resulting in better article-summary and cluster-summary entailment compared to other baselines in both automatic and human evaluations.
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.