Readability Measures and Automatic Text Simplification

ACL ARR 2025 May Submission7225 Authors

Abstract:

Readability is a key concept in our era where textual information is abundant.
Automatic text simplification (ATS) aims at making texts accessible to their
target audience. Lately, there have been studies on the correlations between
evaluation metrics in ATS and human judgment. However, the correlations
between those two aspects and commonly available readability measures have
not been the focus of as much attention. In this work, we investigate the
place of readability measures in ATS by complementing the existing studies
on evaluation metrics and human judgment. We first discuss the relationship between
ATS and research in readability, then we report a study on correlations
between readability measures and human judgment, and between readability measures
and ATS evaluation metrics. We identify that LENS is the metric that
correlates the most with readability measures. We find that for text simplification,
lexical diversity is the type of feature that correlates the most with human
judgment and evaluation metrics.

Paper Type: Long

Research Area: Special Theme (conference specific)

Research Area Keywords: readability, evaluation, simplification

Contribution Types: Data analysis, Position papers

Languages Studied: English

Submission Number: 7225