Read Top News First: A Document Reordering Approach for Multi-Document News Summarization

03/19/2022
by   Chao Zhao, et al.
9

A common method for extractive multi-document news summarization is to re-formulate it as a single-document summarization problem by concatenating all documents as a single meta-document. However, this method neglects the relative importance of documents. We propose a simple approach to reorder the documents according to their relative importance before concatenating and summarizing them. The reordering makes the salient content easier to learn by the summarization model. Experiments show that our approach outperforms previous state-of-the-art methods with more complex architectures.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/26/2017

Detecting (Un)Important Content for Single-Document News Summarization

We present a robust approach for detecting intrinsic sentence importance...
research
01/07/2022

An Unsupervised Masking Objective for Abstractive Multi-Document News Summarization

We show that a simple unsupervised masking objective can approach near s...
research
03/05/2023

Mining both Commonality and Specificity from Multiple Documents for Multi-Document Summarization

The multi-document summarization task requires the designed summarizer t...
research
10/15/2021

Modeling Endorsement for Multi-Document Abstractive Summarization

A crucial difference between single- and multi-document summarization is...
research
06/15/2020

DynE: Dynamic Ensemble Decoding for Multi-Document Summarization

Sequence-to-sequence (s2s) models are the basis for extensive work in na...
research
12/22/2021

Adaptive Beam Search to Enhance On-device Abstractive Summarization

We receive several essential updates on our smartphones in the form of S...
research
09/08/2019

Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses

Sentence position is a strong feature for news summarization, since the ...

Please sign up or login with your details

Forgot password? Click here to reset