End-to-End Compositional Models of Vector-Based Semantics

E2ECMVCS 2022


Artificial Intelligence



Call for Papers
End-to-End Compositional Models of Vector-Based Semantics
15-16 August 2022
Workshop at ESSLLI 2022, National University of Ireland, Galway
https://compositioncalculus.sites.uu.nl/workshop/
## Organisation
Michael Moortgat, Gijs Wijnholds (Utrecht University)
## Invited Speakers
- Mehrnoosh Sadrzadeh (UCL)
- Richard Moot (LIRMM)
- Bob Coecke (Cambridge Quantum Computing)
## Description
Compositionality models the syntax-semantics interface as a
structure-preserving map relating syntactic categories (types) and
derivations to their counterparts in a corresponding meaning algebra. In
a distributional setting, the basic building blocks are vector-based
representations of word meanings (embeddings) obtained from data. These
word meanings then have to be combined into meanings for larger
expressions in a way that reflects the structure of their syntactic
composition.
The workshop focuses on *end-to-end* implementations of such
vector-based compositional architectures. This means not only the
elementary word embeddings are obtained from data, but also the
categories/types and their internal composition so that neural methods
can then be applied to learn how the structure of syntactic derivations
can be systematically mapped to operations on the data-driven word
representations.
On the evaluation side, we welcome work on modern NLP tasks for
evaluating sentence embeddings such as Natural Language Inference,
sentence-level classification, and sentence disambiguation tasks.
Special interest goes out to work that uses compositionality to
investigate the syntactic sensitivity of large-scale language models.
## Topics
The workshop welcomes but is not limited to contributions addressing the
following topics:
- End-to-end models of compositional vector-based semantics
- Supervised and unsupervised models for wide-coverage supertagging
and parsing
- Approaches to learning word/sentence representations
- Tasks and datasets requiring or benefiting from syntax
- Analysis of model performance on syntactically motivated tasks
- Multi-task learning/joint training of syntactic and semantic
representations
- Using compositional methods to assess neural network behaviour
- Explainable models of sentence representation
## Submissions
Submissions consist of papers of up to 12 pages reporting on original
work that has not been published or submitted elsewhere. Each
submissions will be refereed by at least two PC members. You can prepare
your submission using LaTeX, using the EPTCS style available at
http://www.eptcs.org, and upload the pdf to Easychair
(https://www.easychair.org/my/conference?conf=e2ecompvec).
Accepted contributions will be published as a volume of Electronic
Proceedings in Theoretical Computer Science, to be made available to
ESSLLI participants at the time of the event.
In addition, a post-ESSLLI volume is planned with selected
revised/expanded versions of workshop contributions together with
reports on the results of the funding NWO project.
## Important dates
- 16 May 2022: Submission deadline
- 24 June 2022: Notification to authors
- 8 July 2022: Final copy due
- 15-16 August 2022: Workshop
## Program Committee
- Gemma Boleda, Universitat Pompeu Fabra
- Daisuke Bekki, Ochanomizu University
- Stergios Chatzikyriakides, University of Crete
- Stephen Clark, Cambridge Quantum
- Bob Coecke, Cambridge Quantum
- Giuseppe Greco, Vrije Universiteit Amsterdam
- Martha Lewis, Bristol University
- Michael Moortgat, Utrecht University (chair)
- Richard Moot, CNRS/LIRMM Montpellier
- Matthew Purver, Queen Mary University of Londen/Jo┼żef Stefan Institute
- Mehrnoosh Sadrzadeh, University College of London
- Gijs Wijnholds, Utrecht University (chair)
## Funding
NWO project 'A composition calculus for vector-based semantic
modelling with a localization for Dutch' (2017--2022),
https://compositioncalculus.sites.uu.nl/project/