Lune

ACL2021Top-tier venue

Evidence-based Factual Error Correction

James Thorne, Andreas Vlachos

2021Year
14Top-tier citations

Abstract

This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is better supported by evidence. This extends the well-studied task of fact verification by providing a mechanism to correct written texts that are refuted or only partially supported by evidence. We demonstrate that it is feasible to train factual error correction systems from existing fact checking datasets which only contain labeled claims accompanied by evidence, but not the correction. We achieve this by employing a two-stage distant supervision approach that incorporates evidence into masked claims when generating corrections. Our approach, based on the T5 transformer and using retrieved evidence, achieved better results than existing work which used a pointer copy network and gold evidence, producing accurate factual error corrections for 5x more instances in human evaluation and a .125 increase in SARI score. The evaluation is conducted on a dataset of 65,000 instances based on a recent fact verification shared task and we release it to enable further work on the task. 1 John Goodman had the lead role in The Babe. John Goodman had the lead role in # #. John Goodman had the lead role in The Babe.

Ask about this paper

Your agent reads all of it.

Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.

Questions to start from

Your agent calls

Luneget_paper_fulltext

Ask in Lune

Free to start. No credit card required.

lune papers fulltext 6551942e-5f76-439e-af9e-8a79cd564f9f

Cited by top-tier papers14

Ask how each one uses it

Builds on7

Related papers

Dusk over the sea between two cliffs drawn in fine vertical lines