CTTS-2021

First Workshop on Current Trends in Text Simplification (CTTS-2021)

(online event), September 21st, 2021 - Europe/Madrid time zone - Central European Summer Time (CEST)

SEPLN2021 event

Presentation

The Current Trends in Text Simplification 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.. The workshop will an online event held during the SEPLN2021 conference, on September 21th 2021.

Call for papers

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 (Siddharthan 2014; Shardlow 2014; Saggion, 2017; Paetzold & Specia, 2017) 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 (Siddharthan & Mandya 2014; Ferrés et al., 2016), unsupervised corpus-based techniques (Biran et al., 2011; Bott et al., 2012; Paetzold & Specia, 2016), supervised machine learning or statistical machine translation (Specia, 2010; Coster & Kauchak, 2011; Štajner et al., 2015) 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 (Glavaš & Štajner, 2015; Paetzold & Specia, 2016; Nisioi et al. 2017; Scarton & Specia, 2018; Martin et al. 2020; Alva-Manchego et al. 2020), and more specifically end-to-end sequence to sequence, and transformer-based learning methods (Zhao et al., 2018; Martin et al., 2020).

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 (Xu et al., 2016; Sulem et al. 2018a, 2018b), the development of context-aware simplification solutions, the creation of appropriate language resources to support research and evaluation (Saggion et al. 2011; Štajner et al., 2019), the deployment of simplification in real environments for real users (Aluisio et al. 2008; Rello et al., 2013, Saggion et al., 2015; Alonzo et al. 2020; Moreno et al. 2020), the study of discourse factors in text simplification, the identification of factors affecting the readability of a text (François et al. 2015; Venturi et al., 2015; Brunato et al. 2018), 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)

Important Dates

Submission deadline: ~~15th June 2021~~ ~~Extended to 22nd June 2021~~
Accept/Reject Communications: ~~15th July 2021~~
Camera-ready papers due: 22nd August
Publication: September 2021
Workshop date: 21st September 2021

Submissions

We invite long papers (8 pages for content) and short papers and demos (4 pages for content) with unlimited pages for references. Their final versions in the procedings will be given one additional page of content (up to 9 pages for long papers and 5 pages for short papers and demos, respectively) 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 Submission page The paper submission deadline for both long and short workshop paper, and demo description is 15th 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. It also contains DOCX template files.

Registration

The registration form is written in Spanish. Follow this link to the registration form: https://form.jotform.com/cedi2020/inscripcioncedi.
A glossary of translations in English of the Spanish terms in the form can be found at registration information and glossary .

First complete the personal details: title, name, surname (s), affiliation, email (repeat), and contact phone.
Then the specific details for CTTS-2021 registration
- event: SEPLN-WS-IberLEF
- mode for authors/speakers: Online (price 125 €)
- mode for only attendee : "Solo oyente" (price 40 €)
  
  Note: It is important to note that at least one of the authors must register in the Online mode.
Complete the invoice details (your own data or your institutions data, but do not mix them): ID number or passport number, Name (your name or your institution name), Address and city, Zip code, Province or State, and Country
Tick the boxes and click the "Enviar y Pagar" (send and pay) button.
The payment platform uses credit cards. The following credit cards are allowed: VISA, Mastercard, Maestro, Diners Club International, Discover, JCB, and UnionPay.

Note: If you have any doubts or problems with the registration please don't hesitate to ask for help by email to daniel.ferres@upf.edu with CC to horacio.saggion@upf.edu

Program

The workshop will consist of the presentation of long papers, two invited talks and a round table discussion session.

	Online event - 21st September Europe/Madrid time zone - Central European Summer Time (CEST).
12:00 - 12:15	Welcome & Introduction: Horacio Saggion
12:15 - 12:45	Gradient Boosted Trees for Identification of Complex Words in Context Raksha Agarwal and Niladri Chatterjee
12:45 - 13:15	Exploration of Spanish Word Embeddings for Lexical Simplification Rodrigo Alarcon, Lourdes Moreno and Paloma Martínez
13:15 - 14:30	Lunch Break
14:30 - 15:30	Invited Talk 1: Aline Villavicencio What if the whole is greater than the sum of the parts? Modelling Complex (Multiword) Expressions (see Abstract and Bio here)
15:30 - 16:00	DEPSYM: A Lightweight Syntactic Text Simplification Approach using Dependency Trees Niladri Chatterjee and Raksha Agarwal
16:00 - 16:30	The Role of Text Simplification Operations in Evaluation Laura Vásquez-Rodríguez, Matthew Shardlow, Piotr Przybyła and Sophia Ananiadou
16:30 - 17:00	Coffee Break
17:00 - 18:00	Invited Talk 2: Matt Huenerfauth Human-Computer Interaction and Automatic Text Simplification: Understanding the Perspective of Deaf and Hard of Hearing Users (see Abstract and bio here)
18:00 - 18:30	Linguistic Capabilities for a Checklist-based evaluation in Automatic Text Simplification Oscar M. Cumbicus-Pineda, Itziar Gonzalez-Dios and Aitor Soroa
18:30 - 19:00	When the Scale is Unclear -- Analysis of the Interpretation of Rating Scales in Human Evaluation of Text Simplification Regina Stodden
19:00 - 19:30	Round Table: Sanja Štajner
19:30 - 19:45	Closing: Horacio Saggion

Invited Speakers

Matt Huenerfauth (Rochester Institute of Technology, USA).

Invited talk: Human-Computer Interaction and Automatic Text Simplification: Understanding the Perspective of Deaf and Hard of Hearing Users

Aline Villavicencio (University of Sheffield, UK ; Federal University of Rio Grande do Sul, Brazil)

Invited talk: What if the whole is greater than the sum of the parts? Modelling Complex (Multiword) Expressions

Proceedings

The proceedings are published as CEUR Workshop Proceedings at:
Vol-2944 Current Trends in Text Simplification 2021

Camera-Ready Submission

Please find in the following link the instructions for the submission of the camera-ready papers and the authors agreement forms:

Camera-Ready instructions

Programme 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 Lile, France)
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 Lile, France)
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)

Contact

Please send us an email at horacio.saggion@upf.edu if you have any question.

Organising committee

Horacio Saggion	LaSTuS-TALN Universitat Pompeu Fabra, Barcelona, Spain
Sanja Štajner	Symanto Research, Germany
Daniel Ferrés	LaSTuS-TALN Universitat Pompeu Fabra, Barcelona, Spain
Kim Cheng Sheang	LaSTuS-TALN Universitat Pompeu Fabra, Barcelona, Spain