AgreeSum: Agreement-Oriented Multi-Document Summarization
arXiv:2106.02278
Abstract
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.
arXiv commentFindings of ACL 2021
References in corpus (6)
- Professor Forcing: A New Algorithm for Training Recurrent Networks
- Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation
- Detecting Hallucinated Content in Conditional Neural Sequence Generation
- SummAE: Zero-Shot Abstractive Text Summarization using Length-Agnostic Auto-Encoders
- Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference
- Generating Representative Headlines for News Stories