@inproceedings{fujiwara-etal-2026-continuous,
title = "Continuous Difficulty Control for Text Simplification",
author = "Fujiwara, Yuki and
Miyata, Rina and
Kajiwara, Tomoyuki and
Arase, Yuki",
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.677/",
pages = "14216--14227",
ISBN = "979-8-89176-462-0",
abstract = "Controlling text difficulty is crucial for adapting texts to individual language learners. Existing controllable text simplification methods condition generation on discrete proficiency-level tokens, treating these levels as independent categories. As a result, they fail to capture the ordinal structure of language proficiency and cannot provide fine-grained control beyond predefined levels. To address this limitation, we propose a continuous difficulty control method that adjusts simplification difficulty by editing the norm of a conditioning embedding derived from the input sentence semantics. The embedding is incorporated into the transformer decoder through attention-based conditioning, enabling continuous control over output difficulty while modeling ordinal relationships across levels. Unlike token-based approaches, our method supports interpolation between proficiency levels and flexible control over edit magnitude. Experiments on controllable text simplification benchmarks demonstrate improved difficulty controllability, simplification quality, and sentence difficulty estimation performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fujiwara-etal-2026-continuous">
<titleInfo>
<title>Continuous Difficulty Control for Text Simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Fujiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rina</namePart>
<namePart type="family">Miyata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Kajiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Arase</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>Controlling text difficulty is crucial for adapting texts to individual language learners. Existing controllable text simplification methods condition generation on discrete proficiency-level tokens, treating these levels as independent categories. As a result, they fail to capture the ordinal structure of language proficiency and cannot provide fine-grained control beyond predefined levels. To address this limitation, we propose a continuous difficulty control method that adjusts simplification difficulty by editing the norm of a conditioning embedding derived from the input sentence semantics. The embedding is incorporated into the transformer decoder through attention-based conditioning, enabling continuous control over output difficulty while modeling ordinal relationships across levels. Unlike token-based approaches, our method supports interpolation between proficiency levels and flexible control over edit magnitude. Experiments on controllable text simplification benchmarks demonstrate improved difficulty controllability, simplification quality, and sentence difficulty estimation performance.</abstract>
<identifier type="citekey">fujiwara-etal-2026-continuous</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.677/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>14216</start>
<end>14227</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Continuous Difficulty Control for Text Simplification
%A Fujiwara, Yuki
%A Miyata, Rina
%A Kajiwara, Tomoyuki
%A Arase, Yuki
%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 fujiwara-etal-2026-continuous
%X Controlling text difficulty is crucial for adapting texts to individual language learners. Existing controllable text simplification methods condition generation on discrete proficiency-level tokens, treating these levels as independent categories. As a result, they fail to capture the ordinal structure of language proficiency and cannot provide fine-grained control beyond predefined levels. To address this limitation, we propose a continuous difficulty control method that adjusts simplification difficulty by editing the norm of a conditioning embedding derived from the input sentence semantics. The embedding is incorporated into the transformer decoder through attention-based conditioning, enabling continuous control over output difficulty while modeling ordinal relationships across levels. Unlike token-based approaches, our method supports interpolation between proficiency levels and flexible control over edit magnitude. Experiments on controllable text simplification benchmarks demonstrate improved difficulty controllability, simplification quality, and sentence difficulty estimation performance.
%U https://aclanthology.org/2026.findings-emnlp.677/
%P 14216-14227
Markdown (Informal)
[Continuous Difficulty Control for Text Simplification](https://aclanthology.org/2026.findings-emnlp.677/) (Fujiwara et al., Findings 2026)
ACL
- Yuki Fujiwara, Rina Miyata, Tomoyuki Kajiwara, and Yuki Arase. 2026. Continuous Difficulty Control for Text Simplification. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 14216–14227, Budapest, Hungary. Association for Computational Linguistics.