Multi-Document Summarization with Centroid-Based Pretraining

2022/08/01 by Puduppully, Ratish, Jain, Parag, Chen, Nancy F. +1
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2208.01006

Abstract

In Multi-Document Summarization (MDS), the input can be modeled as a set of documents, and the output is its summary. In this paper, we focus on pretraining objectives for MDS. Specifically, we introduce a novel pretraining objective, which involves selecting the ROUGE-based centroid of each document cluster as a proxy for its summary. Our objective thus does not require human written summaries and can be utilized for pretraining on a dataset consisting solely of document sets. Through zero-shot, few-shot, and fully supervised experiments on multiple MDS datasets, we show that our model Centrum is better or comparable to a state-of-the-art model. We make the pretrained and fine-tuned models freely available to the research community https://github.com/ratishsp/centrum.

Related

• Revisiting the Centroid-based Method: A Strong Baseline for Multi-Document Summarization
• Centroid-based summarization of multiple documents: sentence extraction, utility-based evaluation, and user studies
• PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization
• Supervising the Centroid Baseline for Extractive Multi-Document Summarization
• Combining State-of-the-Art Models with Maximal Marginal Relevance for Few-Shot and Zero-Shot Multi-Document Summarization