A Proposition-Level Clustering Approach for Multi-Document Summarization

12/16/2021
by   Ori Ernst, et al.
11

Text clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition. Clusters were leveraged to indicate information saliency and to avoid redundancy. These methods focused on clustering sentences, even though closely related sentences also usually contain non-aligning information. In this work, we revisit the clustering approach, grouping together propositions for more precise information alignment. Specifically, our method detects salient propositions, clusters them into paraphrastic clusters, and generates a representative sentence for each cluster by fusing its propositions. Our summarization method improves over the previous state-of-the-art MDS method in the DUC 2004 and TAC 2011 datasets, both in automatic ROUGE scores and human preference.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/17/2020

SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression

Obtaining training data for multi-document summarization (MDS) is time c...
research
06/20/2017

Graph-based Neural Multi-Document Summarization

We propose a neural multi-document summarization (MDS) system that incor...
research
05/20/2020

A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal

Multi-document summarization (MDS) aims to compress the content in large...
research
09/01/2020

SuperPAL: Supervised Proposition ALignment for Multi-Document Summarization and Derivative Sub-Tasks

Multi-document summarization (MDS) is a challenging task, often decompos...
research
10/09/2021

Extending Multi-Text Sentence Fusion Resources via Pyramid Annotations

NLP models that compare or consolidate information across multiple docum...
research
10/07/2021

HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles

We present HowSumm, a novel large-scale dataset for the task of query-fo...
research
02/22/2022

Learning Cluster Patterns for Abstractive Summarization

Nowadays, pre-trained sequence-to-sequence models such as BERTSUM and BA...

Please sign up or login with your details

Forgot password? Click here to reset