Current Trends in Text Simplification (CTTS-2021) Workshop

Deadline Extension (22 June) and Last Call for Papers

In conjunction with the XXXVII edition of the annual Conference of the Spanish Society for Natural Language Processing (SEPLN).
(online event), September 21st, 2021


*** We are happy to announce that Matt Huenerfauth (Rochester Institute of Technology) will be our invited speaker. ***

Workshop URL: http://www.taln.upf.edu/pages/cttsr2021-ws/

Thanks to the availability of texts on the Web in recent years, increased knowledge and information have been made available to broader audiences. However, the way in which a text is written— vocabulary, syntax, text organization/structure —can be difficult to read and understand for many people, especially those with low literacy, cognitive or linguistic impairment, or those with limited knowledge of the language of the text. Texts containing uncommon words or long and complicated sentences can be difficult to read and understand by people as well as difficult to analyse by machines. Automatic text simplification is the process of transforming a text into another text which, ideally conveying the same message, will be easier to read and understand by a broader audience.

Research in text simplification has been approached from different angles: rule-based linguistically informed methods, unsupervised corpus-based techniques, supervised machine learning or statistical machine translation have all been attempted in text simplification. Recently, research in text simplification has, like in many other natural language processing areas, increased the use of methods derived from the deep learning paradigm, and more specifically end-to-end sequence to sequence, and transformer-based learning methods. In spite of the current advances in the field, there are many important aspects of the simplification problem that need the attention of our community, including but not limited to: the design of appropriate evaluation metrics, the development of context-aware simplification solutions, the creation of appropriate language resources to support research and evaluation, the deployment of simplification in real environments for real users, the study of discourse factors in text simplification, the identification of factors affecting the readability of a text, etc.

The workshop aims at bringing together researchers, developers and industries of assistive technologies, public organizations representatives, and other parties interested in the problem of making information more accessible to all citizens. We will discuss recent trends and developments in the area of automatic text simplification, automatic readability assessment, language resources and evaluation for text simplification, etc.

Topics

The workshop aims to receive contributions in the following topics:

● Lexical Simplification (LS)

● Syntactic Simplification (SS)

● Sequence to Sequence Models for LS and SS

● Modular and End-to-end Text Simplification

● Zero-shot Text Simplification

● Controllable Simplification

● Text Complexity Assessment

● Corpora, Lexical Resources, Benchmarks for Text Simplification

● Studies on Text Simplification Evaluation

● Assistive Technologies for improving readability and comprehension including those going beyond text

● Domain Specific Text Simplification (e.g. health, legal)

● Other Related topics in Text Simplification (e.g. eye-tracking simplification studies)



We invite long papers (8 pages) and short papers and demos (4 pages). Both long and short papers and demos have unlimited references, and their final versions will be given one additional page (up to 9 and 5 pages, respectively, in the proceedings and unlimited pages for references).

CTTS-2021 uses a double-blind reviewing process. Papers must conform to the official CEUR-WS style guidelines, be in PDF format, and be submitted via the Easychair conference management system using this link: Easychair CTTS-2021 (https://easychair.org/conferences/?conf=ctts2021)

The paper submission deadline for both long and short workshop paper, and demo description is 22nd June, 2021.

Multiple submissions policy: Multiple submissions are allowed, but the authors should indicate clearly whether they have submitted or plan to submit a paper with the same content to another venue.

Templates, guidelines and other policies: The CEUR-ART paper style with 1-Colum will be used. An Overleaf page for LaTeX users is available at https://www.overleaf.com/read/gwhxnqcghhdt. You can also download an offline version with the style files from ceur-ws.org/Vol-XXX/CEURART.zip.

Workshop Organizers

Horacio Saggion (Universitat Pompeu Fabra)

Sanja Štajner (ReadableAI)

Daniel Ferrés (Universitat Pompeu Fabra)

Publication

Kim Cheng Sheang (Universitat Pompeu Fabra)

Invited Speakers

Matt Huenerfauth (Rochester Institute of Technology) http://huenerfauth.ist.rit.edu/

Language of the event and publications: English

Program Committee

Rodrigo Alarcón (Universidad Carlos III, Spain)

Sandra Aluísio (University of São Paulo, Brazil)

Fernando Alva Manchego (University of Sheffield, UK)

Susana Bautista (Universidad Francisco de Vitoria, Spain)

Antoine Bordes (Facebook, UK)

Stefan Bott (‎LoveToKnow Corp., Spain)

Remi Cardon (Université de Lille)

Eric De la Clergerie (INRIA, France)

Felice Dell'Orletta (Istituto di Linguistica Computazionale “Antonio Zampolli”, Italy)

Richard Evans (University of Wolverhampton, UK)

Thomas François (Université catholique de Louvain, Belgique)

Nuria Gala (Université Aix-Marseille, France)

Goran Glavaš (University of Mannheim, Germany)

Itziar Gonzalez-Dios (University of the Basque Country, Spain)

Natalia Grabar (Université de Lille)

Raquel Hervás (Universidad Complutense de Madrid, Spain)

David Kauchak (Pomona College, USA)

Elena Lloret (Universidad de Alicante, Spain)

Louis Martin (Facebook, UK)

Lourdes Moreno López (Universidad Carlos III, Spain)

Gustavo Henrique Paetzold (Universidade Tecnológica Federal do Paraná, Brazil)

Benoît Sagot (INRIA, France)

Carolina Scarton (University of Sheffield, UK)

Matthew Shardlow (Manchester Metropolitan University, UK)

Advaith Siddharthan (The Open University, UK) Lucia Specia (Imperial College, UK)

Giulia Venturi (Istituto di Linguistica Computazionale “Antonio Zampolli”, Italy)

Victoria Yaneva (National Board of Medical Examiners, USA)



Workshop Date:

September 21st 2021 (confirmed)

Workshop Schedule (on-line):

Extended Submission deadline: 22nd June 2021

Accept/Reject Communications: 15th July 2021

Camera Ready: 30th July 2021

Related Previous Workshops

Workshops on text simplification and accessibility (NLP4ITA) at LREC 2012 and NAACL 2013. Quality Assessment for Text Simplification collocated with LREC 2016.