Text Fact Transfer
Submission Type: Regular Long Paper
Submission Track: Natural Language Generation
Submission Track 2: Information Extraction
Keywords: Text Generation, Factuality, Text Style Transfer, Information Extraction
TL;DR: We propose the new task of text fact transfer, a complementary task to text style transfer which seeks to transfer factual content while preserving style, along with a model to solve our task
Abstract: Text style transfer is a prominent task that aims to control the style of text without inherently changing its factual content. To cover more text modification applications, such as adapting past news for current events and repurposing educational materials, we propose the task of text fact transfer, which seeks to transfer the factual content of a source text between topics without modifying its style. We find that existing language models struggle with text fact transfer, due to their inability to preserve the specificity and phrasing of the source text, and tendency to hallucinate errors. To address these issues, we design ModQGA, a framework that minimally modifies a source text with a novel combination of end-to-end question generation and specificity-aware question answering. Through experiments on four existing datasets adapted for text fact transfer, we show that ModQGA can accurately transfer factual content without sacrificing the style of the source text.
Submission Number: 2258
Loading