Saved in:
Bibliographic Details
Main Authors: Aharoni, Roee, Narayan, Shashi, Maynez, Joshua, Herzig, Jonathan, Clark, Elizabeth, Lapata, Mirella
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2212.10622
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916081129488384
author Aharoni, Roee
Narayan, Shashi
Maynez, Joshua
Herzig, Jonathan
Clark, Elizabeth
Lapata, Mirella
author_facet Aharoni, Roee
Narayan, Shashi
Maynez, Joshua
Herzig, Jonathan
Clark, Elizabeth
Lapata, Mirella
contents Abstractive summarization has enjoyed renewed interest in recent years, thanks to pre-trained language models and the availability of large-scale datasets. Despite promising results, current models still suffer from generating factually inconsistent summaries, reducing their utility for real-world application. Several recent efforts attempt to address this by devising models that automatically detect factual inconsistencies in machine generated summaries. However, they focus exclusively on English, a language with abundant resources. In this work, we leverage factual consistency evaluation models to improve multilingual summarization. We explore two intuitive approaches to mitigate hallucinations based on the signal provided by a multilingual NLI model, namely data filtering and controlled generation. Experimental results in the 45 languages from the XLSum dataset show gains over strong baselines in both automatic and human evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2212_10622
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle mFACE: Multilingual Summarization with Factual Consistency Evaluation
Aharoni, Roee
Narayan, Shashi
Maynez, Joshua
Herzig, Jonathan
Clark, Elizabeth
Lapata, Mirella
Computation and Language
Abstractive summarization has enjoyed renewed interest in recent years, thanks to pre-trained language models and the availability of large-scale datasets. Despite promising results, current models still suffer from generating factually inconsistent summaries, reducing their utility for real-world application. Several recent efforts attempt to address this by devising models that automatically detect factual inconsistencies in machine generated summaries. However, they focus exclusively on English, a language with abundant resources. In this work, we leverage factual consistency evaluation models to improve multilingual summarization. We explore two intuitive approaches to mitigate hallucinations based on the signal provided by a multilingual NLI model, namely data filtering and controlled generation. Experimental results in the 45 languages from the XLSum dataset show gains over strong baselines in both automatic and human evaluation.
title mFACE: Multilingual Summarization with Factual Consistency Evaluation
topic Computation and Language
url https://arxiv.org/abs/2212.10622