https://github.com/brucewlee/prompt-learning-readability
[EACL 2023] use text-to-text models (BART, T5) for readability assessment
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (10.1%) to scientific vocabulary
Keywords
Repository
[EACL 2023] use text-to-text models (BART, T5) for readability assessment
Basic Info
Statistics
- Stars: 4
- Watchers: 1
- Forks: 2
- Open Issues: 0
- Releases: 0
Topics
Metadata Files
readme.md
Prompt-based Learning for Text Readability Assessment
Overview
This repository hosts research code from our research paper "Prompt-based Learning for Text Readability Assessment" at EACL 2023. You can train and evaluate models using the code here. The included scripts are self-explanatory with comments for easy reading!
Training
Set arguments in utils/train_arguments.py
Testing
Set arguments in utils/test_arguments.py
Citation
@inproceedings{lee-lee-2023-prompt,
title = "Prompt-based Learning for Text Readability Assessment",
author = "Lee, Bruce W. and
Lee, Jason",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.135",
pages = "1819--1824",
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 (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. Our code is available at github.com/brucewlee/prompt-learning-readability.",
}
Please cite our paper and provide link to this repository if you use in this software in research.
Owner
- Name: Bruce W. Lee (이웅성)
- Login: brucewlee
- Kind: user
- Location: Philadelphia, PA
- Company: University of Pennsylvania
- Website: brucewlee.github.io
- Repositories: 3
- Profile: https://github.com/brucewlee
Research Scientist - NLP
GitHub Events
Total
- Watch event: 1
Last Year
- Watch event: 1
Committers
Last synced: over 1 year ago
Top Committers
| Name | Commits | |
|---|---|---|
| Bruce W. Lee | w****e@g****m | 9 |
Issues and Pull Requests
Last synced: 10 months ago
All Time
- Total issues: 0
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0