AgreeSum: Agreement-Oriented Multi-Document Summarization

• URL: http://arxiv.org/abs/2106.02278v1
• Date: Fri, 4 Jun 2021 06:17:49 GMT
• Title: AgreeSum: Agreement-Oriented Multi-Document Summarization
• Authors: Richard Yuanzhe Pang, Adam D. Lelkes, Vinh Q. Tran, Cong Yu
• Abstract summary: Given a cluster of articles, the goal is to provide abstractive summaries that represent information common and faithful to all input articles. We create a dataset for AgreeSum, and provide annotations on articlesummary entailment relations for a subset of the clusters in the dataset.
• Score: 3.4743618614284113
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs [70.15262704746378]
  We propose a systematically created human-annotated dataset consisting of coherent summaries for five publicly available datasets and natural language user feedback. Preliminary experiments with Falcon-40B and Llama-2-13B show significant performance improvements (10% Rouge-L) in terms of producing coherent summaries.
  arXiv  Detail & Related papers  (2024-07-05T20:25:04Z)
• Write Summary Step-by-Step: A Pilot Study of Stepwise Summarization [48.57273563299046]
  We propose the task of Stepwise Summarization, which aims to generate a new appended summary each time a new document is proposed. The appended summary should not only summarize the newly added content but also be coherent with the previous summary. We show that SSG achieves state-of-the-art performance in terms of both automatic metrics and human evaluations.
  arXiv  Detail & Related papers  (2024-06-08T05:37:26Z)
• JADS: A Framework for Self-supervised Joint Aspect Discovery and Summarization [3.992091862806936]
  Our solution integrates topic discovery and summarization into a single step. Given text data, our Joint Aspect Discovery and Summarization algorithm (JADS) discovers aspects from the input. Our proposed method achieves higher semantic alignment with ground truth and is factual.
  arXiv  Detail & Related papers  (2024-05-28T23:01:57Z)
• GUMsley: Evaluating Entity Salience in Summarization for 12 English Genres [14.37990666928991]
  We present and evaluate GUMsley, the first entity salience dataset covering all named and non-named salient entities for 12 genres of English text. We show that predicting or providing salient entities to several model architectures enhances performance and helps derive higher-quality summaries.
  arXiv  Detail & Related papers  (2024-01-31T16:30:50Z)
• On Context Utilization in Summarization with Large Language Models [83.84459732796302]
  Large language models (LLMs) excel in abstractive summarization tasks, delivering fluent and pertinent summaries. Recent advancements have extended their capabilities to handle long-input contexts, exceeding 100k tokens. We conduct the first comprehensive study on context utilization and position bias in summarization.
  arXiv  Detail & Related papers  (2023-10-16T16:45:12Z)
• LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction [42.171703872560286]
  Multi-document summarization is a challenging task due to its inherent subjective bias. We aim to enhance the objectivity of news summarization by focusing on the main event of a group of related news documents.
  arXiv  Detail & Related papers  (2023-10-05T09:38:09Z)
• UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization [54.59104881168188]
  textscUniSumm is a unified few-shot summarization model pre-trained with multiple summarization tasks. textscSummZoo is a new benchmark to better evaluate few-shot summarizers.
  arXiv  Detail & Related papers  (2022-11-17T18:54:47Z)
• ACM -- Attribute Conditioning for Abstractive Multi Document Summarization [0.0]
  We propose a model that incorporates attribute conditioning modules in order to decouple conflicting information by conditioning for a certain attribute in the output summary. This approach shows strong gains in ROUGE score over baseline multi document summarization approaches.
  arXiv  Detail & Related papers  (2022-05-09T00:00:14Z)
• EntSUM: A Data Set for Entity-Centric Summarization [27.845014142019917]
  Controllable summarization aims to provide summaries that take into account user-specified aspects and preferences. We introduce a human-annotated data setSUM for controllable summarization with a focus on named entities as the aspects to control.
  arXiv  Detail & Related papers  (2022-04-05T13:45:54Z)
• Unsupervised Summarization with Customized Granularities [76.26899748972423]
  We propose the first unsupervised multi-granularity summarization framework, GranuSum. By inputting different numbers of events, GranuSum is capable of producing multi-granular summaries in an unsupervised manner.
  arXiv  Detail & Related papers  (2022-01-29T05:56:35Z)
• Understanding the Extent to which Summarization Evaluation Metrics Measure the Information Quality of Summaries [74.28810048824519]
  We analyze the token alignments used by ROUGE and BERTScore to compare summaries. We argue that their scores largely cannot be interpreted as measuring information overlap.
  arXiv  Detail & Related papers  (2020-10-23T15:55:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.