MUHAI is an exciting, complex project that needs interdependent research and development activities to be implemented in parallel or in sequence. To this end, the MUHAI consortium has set-up a series of MICRO-Projects, each is by design instrumental to the overcoming of larger issues and the fulfilment of major project objectives, and entrusted to small, ad-hoc teams of researchers among the project partners.
In this issue, we present four micro-projects which have characterized the MUHAI research throughout the past 9 months.
Scaling Constructional Language Processing: Techniques for Managing Large Search Spaces
Constructionist approaches to language make use of form-meaning pairings, called constructions, to capture all linguistic knowledge that is necessary for comprehending and producing natural language expressions. Language processing consists then in combining the constructions of a grammar in such a way that they solve a given language comprehension or production problem.
The domain of inequality is heavily characterized by causal claims. Multiple researchers in economics, social sciences and humanities have studied the sources of modern inequality. However, modelling their automatic detection in natural language is still an open issue. This research project aims to tackle this gap by detecting explicit causal relationships in Italian texts related to inequality.
Linking Language and Semantic Memory for Building Narratives
IRL, developed by Luc Steels and collaborators, is a parsing technique that captures the semantics of a natural language expression as a network of logical constraints. Determining the meaning of a sentence then amounts to finding consistent assignments of variables that satisfy these constraints.
The main objective of this miniproject is to identify a design solution for MUHAI’s data ecosystem and for the integration of its components. MUHAI, is a project that focuses on human-machine understanding and cooperation, by means of mimicking in machines how humans make sense of experiences.
Within the framework of "Aqua Granda, a digital community memory" initiative, launched in November 2020 by the EU H2020 ODYCCEUS project and Science Gallery Venice, among the main outputs is a book, available in open access. MUHAI was cooperating partner in the organization of the workshop "Archives and AI: Coping with Climate Change", event held in occasion of the launch of the exhibition entitled "Navigating Aqua Granda, a digital community memory".
Event > Bringing Computational Construction Grammar into your Classes and Research
Are you going to Antwerp for the 11th International Conference on Construction Grammar? Register at the hands-on tutorial led by MUHAI partners Paul Van Eecke and Katrien Beuls (VUB), authors of the new textbook "Computational Construction Grammar: A Practical Introduction".