Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension
Transactions of the Association for Computational Linguistics · 2024-04-16 · 12 (00) · 432-448
DOI: 10.1162/tacl_a_00653 ↗At a glance
Journal article in Transactions of the Association for Computational Linguistics, published online on 2024-04-16. Written by Sweta Agrawal and 1 co-authors. Cited 13 times so far (Crossref); 70 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
Automatic text simplification (TS) aims to automate the process of rewriting text to make it easier for people to read. A pre-requisite for TS to be useful is that it should convey information that is consistent with the meaning of the original text. However, current TS evaluation protocols assess system outputs for simplicity and meaning preservation without regard for the document context in which output sentences occur and for how people understand them. In this work, we introduce a human evaluation framework to assess whether simplified texts preserve meaning using reading comprehension questions. With this framework, we conduct a thorough human evaluation of texts by humans and by nine automatic systems. Supervised systems that leverage pre-training knowledge achieve the highest scores on the reading comprehension tasks among the automatic controllable TS systems. However, even the best-performing supervised system struggles with at least 14% of the questions, marking them as “unanswerable” based on simplified content. We further investigate how existing TS evaluation metrics and automatic question-answering systems approximate the human judgments we obtained.
Cite
APA
Agrawal, S., & Carpuat, M. (2024). Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension. Transactions of the Association for Computational Linguistics, 12(00), 432-448. https://doi.org/10.1162/tacl_a_00653
Vancouver
Agrawal S, Carpuat M. Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension. Transactions of the Association for Computational Linguistics. 2024;12(00):432-448. doi:10.1162/tacl_a_00653
BibTeX
@article{Agrawal2024,
author = {Agrawal, Sweta and Carpuat, Marine},
title = {Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension},
journal = {Transactions of the Association for Computational Linguistics},
year = {2024},
volume = {12},
number = {00},
pages = {432--448},
doi = {10.1162/tacl_a_00653}
}
EUVIMED