FrenLyS: A Tool for the Automatic Simplification of French General Language Texts

Rolin, Eva; Langlois, Quentin; Watrin, Patrick; Thomas, François

doi:10.26615/978-954-452-072-4_135

Cited by 6 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most datadriven approaches focus on lexical simplification either for complex word identification, such as Lexi or EASIER, or substitution generation, as in the case of Anita. Another aspect worth discussing is the lack of tools leveraging recent advances in large language models (LLM), even for lexical simplification, although there are exceptions such as Rolin et al (2021) using CamenBERT (Martin et al, 2020). Again, other proposals outside this review, such as Qiang et al (2021), explored LLMs but without developing a tool.…”

Section: Technical Approach For Simplificationmentioning

confidence: 99%

A Review of Research-based Automatic Text Simplification Tools

Espinosa-Zaragoza,

Abreu-Salas,

Lloret

et al. 2023

Proceedings of the Conference Recent Advances in Natural Language Processing - Large Language Models for Natural Language Proce

View full text Add to dashboard Cite

In the age of knowledge, the democratisation of information facilitated through the Internet may not be as pervasive if written language poses challenges to particular sectors of the population. The objective of this paper is to present an overview of research-based automatic text simplification tools. Consequently, we describe aspects such as the language, language phenomena, language levels simplified, approaches, specific target populations these tools are created for (e.g. individuals with cognitive impairment, attention deficit, elderly people, children, language learners), and accessibility and availability considerations. The review of existing studies covering automatic text simplification tools is undergone by searching two databases: Web of Science and Scopus. The eligibility criteria involve text simplification tools with a scientific background in order to ascertain how they operate. This methodology yielded 27 text simplification tools that are further analysed. Some of the main conclusions reached with this review are the lack of resources accessible to the public, the need for customisation to foster the individual's independence by allowing the user to select what s/he finds challenging to understand while not limiting the user's capabilities and the need for more simplification tools in languages other than English, to mention a few.

show abstract

Section: Technical Approach For Simplificationmentioning

confidence: 99%

A Review of Research-based Automatic Text Simplification Tools

Espinosa-Zaragoza,

Abreu-Salas,

Lloret

et al. 2023

Proceedings of the Conference Recent Advances in Natural Language Processing - Large Language Models for Natural Language Proce

View full text Add to dashboard Cite

show abstract

“…For FrenLyS (Rolin et al, 2021 ), instances were selected from two corpora, ALECTOR (Gala et al, 2020 ) and texts from various textbooks. For the instances originating from ALECTOR corpus, complex words were identified based on the information gained from a reading experiment with dyslexic children.…”

Section: Related Workmentioning

confidence: 99%

“…The instructions given to annotators for how to select the right candidates, i.e., to judge candidate fitness in context also varied across the datasets. During the creation of FrenLyS (FR), the annotators were instructed to judge the candidate substitution correct if it does not change original meaning, and to accept hypernyms and hyponyms, and small changes in nuances as correct (Rolin et al, 2021 ). During the creation of CEFR-LS (EN), in contrast, the annotators were instructed to select the given substitution candidate, only if it successfully conveys the nuance of the target word in the specific context and does not affect the meaning of a sentence (Uchida et al, 2018 ).…”

Section: Related Workmentioning

confidence: 99%

“…Evaluation datasets for lexical simplification systems only exist for a handful of languages: English (Specia et al, 2012 ; Horn et al, 2014 ; Paetzold and Specia, 2016a ), French (Rolin et al, 2021 ), Portuguese (Hartmann and Aluísio, 2020 ), Spanish (Alarcón, 2021 ), Japanese (Kajiwara and Yamamoto, 2015 ), and Chinese (Qiang et al, 2021 ). The SemEval-2012 dataset (Specia et al, 2012 ) only evaluates one aspect of English lexical simplification systems, the ranking of the substitution candidates.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Lexical simplification benchmarks for English, Portuguese, and Spanish

Štajner¹,

Ferrés²,

Shardlow³

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

Even in highly-developed countries, as many as 15–30% of the population can only understand texts written using a basic vocabulary. Their understanding of everyday texts is limited, which prevents them from taking an active role in society and making informed decisions regarding healthcare, legal representation, or democratic choice. Lexical simplification is a natural language processing task that aims to make text understandable to everyone by replacing complex vocabulary and expressions with simpler ones, while preserving the original meaning. It has attracted considerable attention in the last 20 years, and fully automatic lexical simplification systems have been proposed for various languages. The main obstacle for the progress of the field is the absence of high-quality datasets for building and evaluating lexical simplification systems. In this study, we present a new benchmark dataset for lexical simplification in English, Spanish, and (Brazilian) Portuguese, and provide details about data selection and annotation procedures, to enable compilation of comparable datasets in other languages and domains. As the first multilingual lexical simplification dataset, where instances in all three languages were selected and annotated using comparable procedures, this is the first dataset that offers a direct comparison of lexical simplification systems for three languages. To showcase the usability of the dataset, we adapt two state-of-the-art lexical simplification systems with differing architectures (neural vs. non-neural) to all three languages (English, Spanish, and Brazilian Portuguese) and evaluate their performances on our new dataset. For a fairer comparison, we use several evaluation measures which capture varied aspects of the systems' efficacy, and discuss their strengths and weaknesses. We find that a state-of-the-art neural lexical simplification system outperforms a state-of-the-art non-neural lexical simplification system in all three languages, according to all evaluation measures. More importantly, we find that the state-of-the-art neural lexical simplification systems perform significantly better for English than for Spanish and Portuguese, thus posing a question if such an architecture can be used for successful lexical simplification in other languages, especially the low-resourced ones.

show abstract

“…The estimation of lexical complexity is only one component in the lexical simplification pipeline, which also involves generating candidates for substitution, ranking them, and assessing their degree of fitness in the given sentence context. Datasets focusing on the latter parts of the pipeline have been published for English (Specia et al, 2012;Horn et al, 2014;Paetzold and Specia, 2016a;Štajner et al, 2022), Japanese (Kajiwara and Yamamoto, 2015;Hading et al, 2016), Portuguese (Hartmann and Aluísio, 2020;North et al, 2022a;Štajner et al, 2022), French (Rolin et al, 2021) con, 2021; Ferrés and Saggion, 2022;Štajner et al, 2022), and Chinese (Qiang et al, 2021).…”

Section: Related Workmentioning

confidence: 99%

PolyU-CBS at TSAR-2022 Shared Task: A Simple, Rank-Based Method for Complex Word Substitution in Two Steps

Chersoni,

Hsu

2022

Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)

View full text Add to dashboard Cite

In this paper, we describe the system we present at the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022) regarding the shared task on Lexical Simplification for English, Portuguese, and Spanish. We proposed an unsupervised approach in two steps: First, we used a masked language model with word masking for each language to extract possible candidates for the replacement of a difficult word; second, we ranked the candidates according to three different Transformer-based metrics. Finally, we determined our list of candidates based on the lowest average rank across different metrics. The results show that our method, based on two simple steps and rankings, can effectively improve the scores among datasets for the task of lexical simplification.

show abstract

FrenLyS: A Tool for the Automatic Simplification of French General Language Texts

Cited by 6 publications

References 23 publications

A Review of Research-based Automatic Text Simplification Tools

A Review of Research-based Automatic Text Simplification Tools

Lexical simplification benchmarks for English, Portuguese, and Spanish

PolyU-CBS at TSAR-2022 Shared Task: A Simple, Rank-Based Method for Complex Word Substitution in Two Steps

Contact Info

Product

Resources

About