English

Multi-Document Summarization with Centroid-Based Pretraining

Computation and Language 2023-06-01 v2

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.

Keywords

Cite

@article{arxiv.2208.01006,
  title  = {Multi-Document Summarization with Centroid-Based Pretraining},
  author = {Ratish Puduppully and Parag Jain and Nancy F. Chen and Mark Steedman},
  journal= {arXiv preprint arXiv:2208.01006},
  year   = {2023}
}

Comments

ACL 2023 camera-ready