TL;DR

We are seeking long research papers, survey papers and position papers on any of the following or related topics:

• Which properties of meaning representations are most desirable, universally.
• Comparisons of types of meaning representations (e.g. fixed-size vs. variable-length) and methods for learning them.
• Techniques of explorations of learned meaning representations.
• Evaluation methodologies for meaning representations, including surveys thereof.
• Extrinsic evaluation by relations to cognitive processes.
• Relation between traditional symbolic meaning representations and the learned continuous ones.
• Broad summaries of psycholinguistic evidence describing properties of meaning representation in the human brain.

Requirements:

• Depending on paper type, we expect most submissions to be 12-20 pages long, longer submissions are also possible.
• The papers do not need to be anonymized.

Submit:

• an abstract (~1 page) by e-mail to jnle-on-sentence-representation@googlegroups.com by 31st July 2018,
• the paper through JNLE submission system by 14th 21st October 2018; follow Instructions for Authors

Details:

• Full call for papers.
• Important dates.

Guest Editors of the special issue:

• Ondřej Bojar (Charles University)
• Raffaella Bernardi (University of Trento)
• Holger Schwenk (Facebook AI Research)
• Bonnie Webber (University of Edinburgh)

Homepage:

• http://ufal.mff.cuni.cz/jnle-on-sentence-representation/