BriefGPT.xyz
Feb, 2023
基于提示的文本易读性评估学习
Prompt-based Learning for Text Readability Assessment
HTML
PDF
Bruce W. Lee, Jason Hyung-Jong Lee
TL;DR
本文采用预训练的seq2seq模型对可读性进行评估，并通过测试不同的输入输出格式/前缀来提高模型性能，在Newsela和OneStopEnglish上实现99.6%和98.7%的成对分类精度。
Abstract
We propose the novel adaptation of a
pre-trained seq2seq model
for
readability assessment
. We prove that a seq2seq model - T5 or BART - can be adapted to discern which text is more difficult from two given texts
→