ACL Findings2021
AgreeSum: Agreement-Oriented Multi-Document Summarization
Richard Yuanzhe Pang, Ádám Dániel Lelkes, Vinh Q. Tran, Cong Yu
摘要
We aim to renew interest in a particular multidocument summarization (MDS) task which we call AgreeSum: agreement-oriented multidocument 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 singledocument 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.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 7 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
- A Unified Retrieval Framework with Document Ranking and EDU Filtering for Multi-document Summarization 引用了 PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
- Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback 引用了 Asking and Answering Questions to Evaluate the Factual Consistency of Summaries
- Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback 引用了 PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
- Asking and Answering Questions to Evaluate the Factual Consistency of Summaries 引用了 BERTScore: Evaluating Text Generation with BERT
引用它的顶会 Paper7
- ExT5: Towards Extreme Multi-Task Scaling for Transfer LearningVamsi Aribandi, Yi Tay, Tal Schuster, Jinfeng Rao 等ICLR 2022 · 237 次引用
- Factually Consistent Summarization via Reinforcement Learning with Textual Entailment FeedbackPaul Roit, Johan Ferret, Lior Shani, Roee Aharoni 等ACL 2023 · 21 次引用
- Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive FeedbackQian Dong, Yiding Liu, Qingyao Ai, Zhijing Wu 等SIGIR 2024 · 9 次引用
- Reward Gaming in Conditional Text GenerationRichard Yuanzhe Pang, Vishakh Padmakumar, Thibault Sellam, Ankur P. Parikh 等ACL 2023 · 2 次引用
- A Unified Retrieval Framework with Document Ranking and EDU Filtering for Multi-document SummarizationShiyin Tan, Jaeeon Park, Dongyuan Li, Renhe Jiang 等SIGIR 2025
它引用的 Paper14
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger 等ICLR 2020 · 8,443 次引用
- PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive SummarizationJingqing Zhang, Yao Zhao, Mohammad Saleh, Peter J. LiuICML 2020 · 2,453 次引用
- Asking and Answering Questions to Evaluate the Factual Consistency of SummariesAlex Wang, Kyunghyun Cho, Mike LewisACL 2020 · 317 次引用
- Heterogeneous Graph Neural Networks for Extractive Document SummarizationDanqing Wang, Pengfei Liu, Yining Zheng, Xipeng Qiu 等ACL 2020 · 275 次引用
- Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?Yada Pruksachatkun, Jason Phang, Haokun Liu, Phu Mon Htut 等ACL 2020 · 168 次引用
相关 Paper
- CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive SummarizationShuyang Cao, Lu WangEMNLP 2021 · 130 次引用
- FaMeSumm: Investigating and Improving Faithfulness of Medical SummarizationNan Zhang, Yusen Zhang, Wu Guo, Prasenjit Mitra 等EMNLP 2023 · 8 次引用
- Towards Improving Faithfulness in Abstractive SummarizationXiuying Chen, Mingzhe Li, Xin Gao, Xiangliang ZhangNeurIPS 2022 · 39 次引用
- ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive SummarizationAlireza Salemi, Emad Kebriaei, Ghazal Neisi Minaei, Azadeh ShakeryEMNLP 2021 · 4 次引用
- Quiz-Style Question Generation for News StoriesÁdám D. Lelkes, Vinh Q. Tran, Cong YuWWW 2021 · 48 次引用
