All deadlines are 11:59PM UTC-12:00 (“anywhere on Earth”).
The organisers are pleased to present the third instalment of the annual workshop on Text Simplification, Accessibility and Readability (TSAR 2024). TSAR aims to provide a cohesive environment to draw members of the computational linguistics, natural language processing and artificial intelligence communities working on the use of automated techniques to make language accessible for all. Previous editions of the workshop have been held at EMNLP in 2022 and RANLP in 2023 with significant engagement and participation driving research and building community in the fields of Text Simplification, Accessibility and Readability.
Research in automatic text simplification (TS) has often focused on proposing the use of methods derived from the deep learning paradigm (Glavaš and Štajner, 2015; Paetzold and Specia, 2016; Nisioi et al., 2017; Zhang and Lapata, 2017; Martin et al., 2020; Maddela et al., 2021; Sheang and Saggion, 2021). Recently, work in text simplification has leveraged the new era of foundational large language models through fine-tuning and prompt-engineering to produce simplifications (Kew et al. 2023; Cripwell et al. 2023; Farajidizaji et al. 2024).
However, there are many important aspects in automatic TS that require the attention of our community: the design of appropriate evaluation metrics (Štajner et al., 2022), the development of context-aware simplification solutions (Yimam et al., 2018; Shardlow et al., 2022a; Saggion et al., 2022), the creation of appropriate language resources to support research and evaluation (Maddela and Xu, 2018; Shardlow et al., 2020; Ferres and Saggion, 2022; North et al., 2022), the deployment of simplification in real environments for real users (Lee and Yeung, 2018; Alonzo et al., 2022), the study of discourse factors in text simplification (Zhong et al., 2019), the identification of factors affecting the readability of a text (Shardlow et al., 2022b), among others. To overcome those issues, there is a need for collaboration of CL/NLP researchers, machine learning and deep learning researchers, UI/UX and Accessibility professionals, as well as public organisations representatives (Štajner, 2021).
Research on automatic text simplification, textual accessibility, and readability have the potential to improve social inclusion of marginalized populations. These related research areas have attracted attention in the past ten years, evidenced by the growing number of publications in NLP conferences. While only about 300 articles in Google Scholar mentioned TS in 2010, this number has increased to about 600 in 2015 and greater than 1000 in 2020 (Štajner, 2021). This number has certainly increased rapidly since 2020, at the recent LREC-COLING 2024 conference there were 50 new papers presented on related topics across the main conference and associated workshops.
The TSAR 2024 workshop builds upon the recent success of several regional workshops that covered a subset of our topics of interest, including READI Workshops at LREC 2022 and LREC 2024, SEPLN 2021 Workshop on Current Trends in Text Simplification (CTTS)), the SimpleText workshop at CLEF 2021, as well as the birds-of-a-feather events on Text Simplification at NAACL 2021 (over 50 participants), ACL 2022 and EMNLP 2023.
Submissions to the workshop will be organised into two tracks, a main track and a special track with a focus on evaluation.
The main track will invite contributions on the following topics, aligned with previous editions of the workshop:
The special track will focus on Evaluation of Text Simplification and Readability Systems. Papers in this track will be ranked and assessed separately to those in the main track. Topics include, but are not limited to:
We welcome three types of papers: long papers, short papers and demos. Submissions should be made to via START.
The papers should present novel research. The review will be double blind and thus all submissions should be anonymized.
Long and Short Papers: We adhere to the same guidelines as EMNLP 2024.
Demo Papers: Demos should be no more than two (2) pages, including references, and should describe implemented systems related to the topics of interest of the workshop. It also should include a link to a short screencast of the working software. In addition, authors of demo papers must be willing to present a demo of their system during TSAR 2024.
All submissions must be made via the workshop START page (link above). Organisers will not be able to accept submissions made after the workshop deadline, or made via email. All information including the authors lists and affiliations should be finalised prior to submission and will not be modifiable after acceptance. Participants should mark their desired track at submission time (main or special track). The organisers will not be able to move papers between tracks after the end of the submission period. Submissions that do not conform to the required styles, including paper size, margin width, and font size restrictions, will be rejected without review.