Multi-Fact Correction in Abstractive Text Summarization
release_5o7thl7smbewlauzaijlm7y3zu
by
Yue Dong, Shuohang Wang, Zhe Gan, Yu Cheng, Jackie Chi Kit Cheung, Jingjing Liu
2020
Abstract
Pre-trained neural abstractive summarization systems have dominated
extractive strategies on news summarization performance, at least in terms of
ROUGE. However, system-generated abstractive summaries often face the pitfall
of factual inconsistency: generating incorrect facts with respect to the source
text. To address this challenge, we propose Span-Fact, a suite of two factual
correction models that leverages knowledge learned from question answering
models to make corrections in system-generated summaries via span selection.
Our models employ single or multi-masking strategies to either iteratively or
auto-regressively replace entities in order to ensure semantic consistency
w.r.t. the source text, while retaining the syntactic structure of summaries
generated by abstractive summarization models. Experiments show that our models
significantly boost the factual consistency of system-generated summaries
without sacrificing summary quality in terms of both automatic metrics and
human evaluation.
In text/plain
format
Archived Files and Locations
application/pdf 1.0 MB
file_gcmbzm6hmzhubddobwsiy3fcfa
|
arxiv.org (repository) web.archive.org (webarchive) |
2010.02443v1
access all versions, variants, and formats of this works (eg, pre-prints)