Saved in:
Bibliographic Details
Main Authors: Lee, Bruce W., Lee, Jason Hyung-Jong
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2302.13139
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914835706413056
author Lee, Bruce W.
Lee, Jason Hyung-Jong
author_facet Lee, Bruce W.
Lee, Jason Hyung-Jong
contents 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 (pairwise). As an exploratory study to prompt-learn a neural network for text readability in a text-to-text manner, we report useful tips for future work in seq2seq training and ranking-based approach to readability assessment. Specifically, we test nine input-output formats/prefixes and show that they can significantly influence the final model performance. Also, we argue that the combination of text-to-text training and pairwise ranking setup 1) enables leveraging multiple parallel text simplification data for teaching readability and 2) trains a neural model for the general concept of readability (therefore, better cross-domain generalization). At last, we report a 99.6% pairwise classification accuracy on Newsela and a 98.7% for OneStopEnglish, through a joint training approach.
format Preprint
id arxiv_https___arxiv_org_abs_2302_13139
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Prompt-based Learning for Text Readability Assessment
Lee, Bruce W.
Lee, Jason Hyung-Jong
Computation and Language
Artificial Intelligence
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 (pairwise). As an exploratory study to prompt-learn a neural network for text readability in a text-to-text manner, we report useful tips for future work in seq2seq training and ranking-based approach to readability assessment. Specifically, we test nine input-output formats/prefixes and show that they can significantly influence the final model performance. Also, we argue that the combination of text-to-text training and pairwise ranking setup 1) enables leveraging multiple parallel text simplification data for teaching readability and 2) trains a neural model for the general concept of readability (therefore, better cross-domain generalization). At last, we report a 99.6% pairwise classification accuracy on Newsela and a 98.7% for OneStopEnglish, through a joint training approach.
title Prompt-based Learning for Text Readability Assessment
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2302.13139