SimpleText@CLEF-2021 Workshop: Text Simplification for Scientific Information Access
You can read the preprint of our <a href=”https://hal.archives-ouvertes.fr/hal-03121986/document”>CLEF Paper</a> @ <a href=”https://www.ecir2021.eu/”>ECIR-2021</a>
How to cite: Liana Ermakova, Patrice Bellot, Pavel Braslavski, Jaap Kamps, Josiane Mothe, et al. Text Simplification for Scientific Information Access. 43rd edition of the annual BCS-IRSG European Conference on Information Retrieval : Advances in Information Retrieval (ECIR 2021), Mar 2021, Lucca (virtual), Italy. Ffhal-03121986f
https://hal.archives-ouvertes.fr/hal-03121986/document
Pilot tasks guidelines: https://simpletext-madics.github.io/data/Guideline-SimpleText-2021.pdf
CFP SimpleText@CLEF: https://simpletext-madics.github.io/2021/clef/CFP-SimpleText%40CLEF.pdf
The goal of this new workshop is to create a community interested in generating a simplified summary of scientific documents.
Open science is the growing movement to make science open, which includes much more than open access (). Indeed, just focusing on scientific opening the science and results they contain. Scientific publications are difficult to understand for people outside the domain and so it is likely they will not read them at all even if they have access to them.
The popularization of science and scientific journalism is one of UNESCO’s oldest programs[1]. In scientific journalism, “journalists serve as intermediaries presenting analyses to the public, but they must also provide the public with the means to reproduce their analyses” (Lynch, 2012). Thus, scientific stories include primary sources allowing the reader to verify a document’s information. In contrast to newspapers limited by the size of the page, digital technologies provide essentially unbounded capabilities for hosting primary-source documents. However, human simplification of scientific documents is very expensive and time consuming. Users cannot have an instant, simplified summary on a specific topic they are interested in.
Although few studies have been carried out in the field of automatic text simplification (Shardlow, 2014) (Liu et al., 2018); it still remains a challengeable task, specifically in the multilingual case.
The goal of this workshop is to create a simplified summary of multiple scientific documents based on a given query which provides the user with an instant simplified summary on a specific topic he/she is interested in or to generate a daily digest for example for ArXiv.
Eva Mendez, Rebecca Lawrence, Catriona J. MacCallum, Eva Moar, together with all the members of the Open Science Policy Platform, Progress on Open Science: Towards a Shared Research Knowledge System, Final Report of the Open Science Policy Platform, 2020.
Lisa Lynch, « “That’s Not Leaking, It’s Pure Editorial”: Wikileaks, Scientific Journalism and Journalistic Enterprise », Can. J. Media Stud. Spec. Issue Fall 2012, [En ligne]. Disponible sur: https://cjms.fims.uwo.ca/issues/special/Lynch.pdf.
Matthew Shardlow, « A Survey of Automated Text Simplification », Int. J. Adv. Comput. Sci. Appl., vol. 4, no 1, 2014, doi: 10.14569/SpecialIssue.2014.040109.
Peter J. Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, Noam Shazeer , « Generating Wikipedia by Summarizing Long Sequences », ArXiv180110198 Cs, janv. 2018, Consulté le: juin 05, 2020. [En ligne]. Disponible sur: http://arxiv.org/abs/1801.10198.
[1] http://www.unesco.org/new/en/natural-sciences/science-technology/sti-policy/global-focus/science-popularization/#:~:text=Science%20Popularization,in%20a%20specific%20scientific%20domain.