[Corpora-List] CMCL – First Call for Papers, Announcement of Shared Task on Eye-Tracking Data Prediction

Enrico Santus esantus at gmail.com
Mon Dec 14 16:56:55 CET 2020

The Workshop on Cognitive Modeling and Computational Linguistics, June 10 2021

Co-located with NAACL 2021

*Workshop Description*

Cognitive Modeling and Computational Linguistics (CMCL) 2021 is a one-day workshop held in conjunction with the conference of the North American Chapter of the Association for Computational Linguistics (NAACL). The goal of CMCL is providing a venue for computational research on cognitive theories of language processing, representation and acquisition. The 2020 workshop follows in the tradition of earlier meetings at ACL 2010, ACL 2011, NAACL-HLT 2012, ACL 2013, ACL 2014, NAACL 2015, EACL 2017, LSA 2018, NAACL 2019 and EMNLP 2020.

*Workshop submissions*

We accept three categories of papers: regular workshop papers, extended abstracts and cross-submissions. Only regular workshop papers will be included in the proceedings as archival publications. All submissions should be in PDF format and made through the Softconf website (link not available yet). To facilitate double-blind reviewing, submitted manuscripts should not include any identifying information about the authors. Submissions with associated preprints (e.g. arXiv) will be considered. Submissions must be formatted using NAACL 2021 templates, available at: https://2021.naacl.org/calls/style-and-formatting/. <https://2021.naacl.org/calls/style-and-formatting/>

*Regular Workshop Papers* can be either full (8 pages of content + references) or short papers (4 pages + references) reporting original and unpublished research that combines cognitive modeling and computational linguistics. *If a workshop paper has been submitted elsewhere, the authors have to declare it at submission time. Papers to be presented at CMCL 2021 must be withdrawn from other venues**.*

*Extended Abstracts* (from 2 to 4 pages + references) describe preliminary work or results that have not been published before. Accepted abstracts will be presented at the workshop, but will not be included in the workshop proceedings.

We will also accept *cross-submissions* (from 2 to 4 pages + references) for papers on related topics that have already appeared in a non-NLP venue (e.g. CogSci). These papers will be presented at the workshop, but will not be included in the proceedings. Interested authors are asked to add a note on the original venue in the submission.


Eye-tracking provides millisecond-accurate records on where humans look when they are reading and are useful in explanatory research of language processing. Being able to accurately predict eye-tracking features will advance the field's understanding of language processing. The use of a standardized dataset will facilitate comparisons between models and the analysis of their varying capabilities.

In this shared task, we present the challenge of predicting eye tracking-based metrics recorded during English sentence processing. We are interested in both cognitive modelling approaches as well as linguistically motivated approaches (e.g., language models) for submission. The shared task will be formulated as a regression task to predict 5 eye-tracking features from the ZuCo corpus <https://www.nature.com/articles/sdata2018291>: number of fixations, first fixation duration, total reading, go-past time, and fixation proportion.

More details will be available soon on the CMCL website. The trial data will be released on January 15, 2021.

For more info on the shared task: cmcl2021sharedtask at gmail.com

*Important Dates*

*Submission deadline: March 9, 2021 *Notification of acceptance: April 12, 2021 Camera-ready version due: April 26, 2021 Workshop date: June 10, 2021

All deadlines are 11:59 PM (UTC-12:00)

*Invited Speakers*

Marco Baroni (Facebook AI – Pompeu Fabra University of Barcelona)

Zoya Bylinskii (Adobe Research)

*Workshop Organizers*

Emmanuele Chersoni (Hong Kong Polytechnic University)

Nora Hollenstein (ETH Zurich) Cassandra Jacobs (University of Wisconsin) Yohei Oseki (University of Tokyo) Laurent Prévot (Aix-Marseille University) Enrico Santus (Bayer Pharmaceuticals)



*Sponsoring Institutions*

Japan Society for the Promotion of Science

Laboratoire Parole et Langage, CNRS, France


cmclorganizers2021 at gmail.com


-- Currently: Senior Data Scientist at Bayer Previously: Postdoc Associate at CSAIL, MIT

Curriculum: www.esantus.com

E-mail: esantus at gmail.com Skype: esantus Phone (US): +1 857-285-1424 -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 20443 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20201214/f5d4ae2c/attachment.txt>

More information about the Corpora mailing list