@inproceedings{vendeville-etal-2026-beyond,
title = "Beyond Lexical and Syntactic: Better Text Simplicity Analysis Informed by Psycholinguistic Research",
author = "Vendeville, Benjamin and
Ermakova, Liana and
De Loor, Pierre",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2159/",
pages = "46173--46191",
ISBN = "979-8-89176-462-0",
abstract = "Automatic text simplification measures correlate poorly with human judgments and are disconnected from psycholinguistic research on comprehension. We propose a multidimensional analysis framework grounded in Cognitive Load Theory and the Construction-Integration model, organizing over 400 linguistic features into six simplicity dimensions targeting distinct comprehension stages. Using this framework, we analyze four human-annotated and six aligned simplification datasets. We find that (1) our dimensions predict human simplicity judgments better than established measures on most datasets; (2) current datasets overwhelmingly target lexical and syntactic dimensions while under-targeting personalization the dimension psychological research identifies as most impactful for comprehension; and (3) existing measures overall do not capture any specific dimension. These findings provide actionable guidance for building measures and datasets better aligned with how readers actually process text."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vendeville-etal-2026-beyond">
<titleInfo>
<title>Beyond Lexical and Syntactic: Better Text Simplicity Analysis Informed by Psycholinguistic Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Vendeville</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liana</namePart>
<namePart type="family">Ermakova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">De Loor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Automatic text simplification measures correlate poorly with human judgments and are disconnected from psycholinguistic research on comprehension. We propose a multidimensional analysis framework grounded in Cognitive Load Theory and the Construction-Integration model, organizing over 400 linguistic features into six simplicity dimensions targeting distinct comprehension stages. Using this framework, we analyze four human-annotated and six aligned simplification datasets. We find that (1) our dimensions predict human simplicity judgments better than established measures on most datasets; (2) current datasets overwhelmingly target lexical and syntactic dimensions while under-targeting personalization the dimension psychological research identifies as most impactful for comprehension; and (3) existing measures overall do not capture any specific dimension. These findings provide actionable guidance for building measures and datasets better aligned with how readers actually process text.</abstract>
<identifier type="citekey">vendeville-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2159/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>46173</start>
<end>46191</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Lexical and Syntactic: Better Text Simplicity Analysis Informed by Psycholinguistic Research
%A Vendeville, Benjamin
%A Ermakova, Liana
%A De Loor, Pierre
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F vendeville-etal-2026-beyond
%X Automatic text simplification measures correlate poorly with human judgments and are disconnected from psycholinguistic research on comprehension. We propose a multidimensional analysis framework grounded in Cognitive Load Theory and the Construction-Integration model, organizing over 400 linguistic features into six simplicity dimensions targeting distinct comprehension stages. Using this framework, we analyze four human-annotated and six aligned simplification datasets. We find that (1) our dimensions predict human simplicity judgments better than established measures on most datasets; (2) current datasets overwhelmingly target lexical and syntactic dimensions while under-targeting personalization the dimension psychological research identifies as most impactful for comprehension; and (3) existing measures overall do not capture any specific dimension. These findings provide actionable guidance for building measures and datasets better aligned with how readers actually process text.
%U https://aclanthology.org/2026.findings-emnlp.2159/
%P 46173-46191
Markdown (Informal)
[Beyond Lexical and Syntactic: Better Text Simplicity Analysis Informed by Psycholinguistic Research](https://aclanthology.org/2026.findings-emnlp.2159/) (Vendeville et al., Findings 2026)
ACL