# Fact-based Text Editing

Source: [Fact-based Text Editing](<https://www.sota2.com/research/paper/68fa69b21e209131cea23826>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:18:29.762Z

Authors: Hayate Iso, Chao Qiao, Hang Li

Published: 2020-07-02T06:50:30.000Z

## Abstract

We propose a novel text editing task, referred to as \\textit{fact-based text editing}, in which the goal is to revise a given document to better describe the facts in a knowledge base (e.g., several triples). The task is important in practice because reflecting the truth is a common requirement in text editing. First, we propose a method for automatically generating a dataset for research on fact-based text editing, where each instance consists of a draft text, a revised text, and several facts represented in triples. We apply the method into two public table-to-text datasets, obtaining two new datasets consisting of 233k and 37k instances, respectively. Next, we propose a new neural network architecture for fact-based text editing, called \\textsc{FactEditor}, which edits a draft text by referring to given facts using a buffer, a stream, and a memory. A straightforward approach to address the problem would be to employ an encoder-decoder model. Our experimental results on the two datasets show that \\textsc{FactEditor} outperforms the encoder-decoder approach in terms of fidelity and fluency. The results also show that \\textsc{FactEditor} conducts inference faster than the encoder-decoder approach.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Fact-based Text Editing on ROTOEDIT (test)](<https://www.sota2.com/research/sota/fact-based-text-editing-on-rotoedit-test.md>): Fact-based Text Editing; ROTOEDIT (test); BLEU: 84.43.

- [Fact-based text editing on WEBEDIT](<https://www.sota2.com/research/sota/fact-based-text-editing-on-webedit.md>): Fact-based Text Editing; WEBEDIT; BLEU: 75.68.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2007.00916>)

[PDF](<https://arxiv.org/pdf/2007.00916.pdf>)

[Implementation](<https://github.com/isomap/factedit>)