Home > Research > Publications & Outputs > Deep learning approaches to lexical simplification

Research

Links

Text available via DOI:

View graph of relations

Deep learning approaches to lexical simplification: A survey

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Deep learning approaches to lexical simplification: A survey. / North, Kai; Ranasinghe, Tharindu; Shardlow, Matthew et al.
In: Journal of Intelligent Information Systems, Vol. 63, No. 1, 28.02.2025, p. 111-134.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

North, K, Ranasinghe, T, Shardlow, M & Zampieri, M 2025, 'Deep learning approaches to lexical simplification: A survey', Journal of Intelligent Information Systems, vol. 63, no. 1, pp. 111-134. https://doi.org/10.1007/s10844-024-00882-9

APA

North, K., Ranasinghe, T., Shardlow, M., & Zampieri, M. (2025). Deep learning approaches to lexical simplification: A survey. Journal of Intelligent Information Systems, 63(1), 111-134. https://doi.org/10.1007/s10844-024-00882-9

Vancouver

North K, Ranasinghe T, Shardlow M, Zampieri M. Deep learning approaches to lexical simplification: A survey. Journal of Intelligent Information Systems. 2025 Feb 28;63(1):111-134. Epub 2024 Sept 2. doi: 10.1007/s10844-024-00882-9

Author

North, Kai ; Ranasinghe, Tharindu ; Shardlow, Matthew et al. / Deep learning approaches to lexical simplification : A survey. In: Journal of Intelligent Information Systems. 2025 ; Vol. 63, No. 1. pp. 111-134.

Bibtex

@article{fa28b4db2bb14727821b99e8006bc248,
title = "Deep learning approaches to lexical simplification: A survey",
abstract = "Lexical Simplification (LS) is the task of substituting complex words within a sentence for simpler alternatives while maintaining the sentence{\textquoteright}s original meaning. LS is the lexical component of Text Simplification (TS) systems with the aim of improving accessibility to various target populations such as individuals with low literacy or reading disabilities. Prior surveys have been published several years before the introduction of transformers, transformer-based large language models (LLMs), and prompt learning that have drastically changed the field of NLP. The high performance of these models has sparked renewed interest in LS. To reflect these recent advances, we present a comprehensive survey of papers published since 2017 on LS and its sub-tasks focusing on deep learning. Finally, we describe available benchmark datasets for the future development of LS systems.",
author = "Kai North and Tharindu Ranasinghe and Matthew Shardlow and Marcos Zampieri",
year = "2025",
month = feb,
day = "28",
doi = "10.1007/s10844-024-00882-9",
language = "English",
volume = "63",
pages = "111--134",
journal = "Journal of Intelligent Information Systems",
issn = "1573-7675",
publisher = "Springer",
number = "1",

}

RIS

TY - JOUR

T1 - Deep learning approaches to lexical simplification

T2 - A survey

AU - North, Kai

AU - Ranasinghe, Tharindu

AU - Shardlow, Matthew

AU - Zampieri, Marcos

PY - 2025/2/28

Y1 - 2025/2/28

N2 - Lexical Simplification (LS) is the task of substituting complex words within a sentence for simpler alternatives while maintaining the sentence’s original meaning. LS is the lexical component of Text Simplification (TS) systems with the aim of improving accessibility to various target populations such as individuals with low literacy or reading disabilities. Prior surveys have been published several years before the introduction of transformers, transformer-based large language models (LLMs), and prompt learning that have drastically changed the field of NLP. The high performance of these models has sparked renewed interest in LS. To reflect these recent advances, we present a comprehensive survey of papers published since 2017 on LS and its sub-tasks focusing on deep learning. Finally, we describe available benchmark datasets for the future development of LS systems.

AB - Lexical Simplification (LS) is the task of substituting complex words within a sentence for simpler alternatives while maintaining the sentence’s original meaning. LS is the lexical component of Text Simplification (TS) systems with the aim of improving accessibility to various target populations such as individuals with low literacy or reading disabilities. Prior surveys have been published several years before the introduction of transformers, transformer-based large language models (LLMs), and prompt learning that have drastically changed the field of NLP. The high performance of these models has sparked renewed interest in LS. To reflect these recent advances, we present a comprehensive survey of papers published since 2017 on LS and its sub-tasks focusing on deep learning. Finally, we describe available benchmark datasets for the future development of LS systems.

U2 - 10.1007/s10844-024-00882-9

DO - 10.1007/s10844-024-00882-9

M3 - Journal article

VL - 63

SP - 111

EP - 134

JO - Journal of Intelligent Information Systems

JF - Journal of Intelligent Information Systems

SN - 1573-7675

IS - 1

ER -