The CLIC is an interdisciplinary group of researchers interested in studying verbal and non-verbal communication.

Our current research spans three areas:

Theoretical linguistics and its relation to human cognition: we study the role of language in various cognitive abilities, developing theoretical and computational models of the structure of human language, of how it is learned and represented in the brain, and which of its properties may be due to biological constraints. We address these questions using interdisciplinary methods and tools that include corpora research, models with neural networks and neuroimaging techniques.

Computational models of multimodality: we aim at understanding multimodal communication, in which intelligent agents can converse using information received through text, images or sounds. Our research tries to understand the role of these different modalities in learning certain reasoning skills. Both the linguistic / cognitive aspects and the possible technological applications of this type of model are considered.

Computational semantics: we aim at developing a cognitively plausible theory of the relationship between the meaning of linguistic expressions and the external world. To this end, we build computational models that combine theories of formal extensional linguistics with conceptual representations based on data. The ultimate goal is to understand how human beings manage to manipulate meaning in a compositional way, to interpret the outside world and act upon it.


Our datasets and pretrained models:


* SICK (Sentences Involving Compositional Knowledge) 

* Distributional Memory (DM)

* "Don't count, predict" vectors

* Other datasets from the COMPOSES project


DISSECT toolkit for creating distributional semantics spaces

* GitHub link

* Documentation for the DISSECT toolkit




Created by daniele.patoner. Last Modification: Thursday 19 of September, 2019 14:47:07 CEST by aurelie.herbelot.