Semantic spaces, vector embeddings

Related to cognition, ML and NL


Workshop on Semantic Spaces at the Intersection of NLP, Physics, and
Cognitive Sciences
https://sites.google.com/view/semspace2020/home <
https://sites.google.com/view/semspace2020/home>

August 6th and 7th 2020
online

****
Registration is now open for SemSpace2020 at
https://sites.google.com/view/semspace2020/registration. Registration is
free, but please do register for planning purposes.

AIMS AND SCOPE
Vector embeddings of word meanings have become a mainstream tool in large
scale natural language processing tools. The use of vectors to represent
meanings in semantic spaces or feature spaces is also employed in cognitive
science. Unrelated to natural language and cognitive science, vectors and
vector spaces have been extensively used as models of physical theories and
especially the theory of quantum mechanics. Crucial similarities between
the vector representations of quantum mechanics and those of natural
language are exhibited via bicompact linear logic and compact closed
categorical structures in natural language.

Exploiting the common ground provided by vector spaces, the proposed
workshop will bring together researchers working at the intersection of
NLP, cognitive science, and physics, offering to them an appropriate forum
for presenting their uniquely motivated work and ideas. The interplay
between these three disciplines will foster theoretically motivated
approaches to understanding how meanings of words interact with each other
in sentences and discourse via grammatical types, how they are determined
by input from the world, and how word and sentence meanings interact
logically.

Topics of interest include (but are not restricted to):
Reasoning in semantic spaces
Compositionality in semantic spaces and conceptual spaces
Conceptual spaces in linguistics and natural language processing
Applications of quantum logic in natural language processing and cognitive
science
Modelling functional words such as prepositions and relative pronouns in
compositional distributional models of meaning
Diagrammatic reasoning for natural language processing and cognitive science
Modelling so-called ‘non-compositional’ phenomena such as metaphor

INVITED SPEAKERS
Jennifer Culbertson, University of Edinburgh
Andrea E. Martin, Max Planck Institute for Psycholinguistics and Radboud
University, Nijmegen

LIST OF ACCEPTED TALKS (in no particular order)
(see also https://sites.google.com/view/semspace2020/programme <
https://sites.google.com/view/semspace2020/programme>)
Russell Richie and Sudeep Bhatia: Similarity judgment within and across
categories: A comprehensive model comparison
James Hefford, Vincent Wang and Matthew Wilson: Categories of Semantic
Concepts
Sean Tull and Johannes Kleiner: Integrated Information in Process Theories
Sonia Cenceschi, Licia Sbattella and Roberto Tedesco: CALLIOPE: a
multi-dimensional model for the prosodic characterisation of Information
Units
Tiffany Duneau: Solving logical puzzles in DisCoCirc
Konstantinos Meichanetzidis, Stefano Gogioso, Giovanni De Felice, Alexis
Toumi, Nicolo Chiappori and Bob Coecke: Quantum Natural Language Processing
on Near-Term Quantum Computers
Sergey Slavnov: Cobordisms and commutative categorial grammars
Sean Tull: Monoidal Categories for Formal Concept Analysis
Lachlan McPheat, Mehrnoosh Sadrzadeh, Adriana Correia and Alexis Toumi:
Derivations and Vector Semantics of Anaphora with Ellipsis in Lambek
Calculus with a Relevant Modality
Sanjaye Ramgoolam, Mehrnoosh Sadrzadeh and Lewis Sword: Gaussianity and
typicality in matrix distributional semantics
Gemma De Las Cuevas, Andreas Klinger, Martha Lewis and Tim Netzer: Cats
climb entails mammals move: preserving hyponymy in compositional
distributional semantics
Whitney Tabor: On the relationship between syntactic and semantic encoding
in vector space language models

Please send any queries to semspace2020@easychair.org <mailto:
semspace2020@easychair.org>

PROGRAMME COMMITTEE
Bob Coecke, University of Oxford
Stefano Gogioso, University of Oxford
Giuseppe Greco, Utrecht University
Peter Gärdenfors, Lund University
Helle Hvid Hansen, Delft University of Technology
Jules Hedges, Max Planck Institute for Mathematics in the Sciences
Peter Hines, University of York
Alexander Kurz, Chapman University
Antonio Lieto, University of Turin, Department of Computer Science
Dan Marsden, University of Oxford
Michael Moortgat, Utrecht University
Richard Moot, CNRS (LIRMM) & University of Montpellier
Dusko Pavlovic, University of Hawaii
Emmanuel Pothos, City University London
Matthew Purver, Queen Mary University of London
Mehrnoosh Sadrzadeh, University College London
Giovanni Sileno, University of Amsterdam
Pawel Sobocinski, Tallinn University of Technology
Oriol Valentín, Universitat Politècnica de Catalunya
Dominic Widdows, Grab
Geraint Wiggins, Vrije Universiteit Brussel / Queen Mary University of
London
Gijs Wijnholds, Utrecht University
Frank Zenker, Lund University

ORGANIZATION COMMITTEE
Martha Lewis, ILLC, University of Amsterdam
Michael Moortgat, Utrecht University
########################################################################
T