This report describes the system developed by the CRIM team for the hypernym discovery task at SemEval 2018. This system exploits a combination of supervised projection learning and unsupervised pattern-based hypernym discovery. It was ranked first on the 3 sub-tasks for which we submitted results. 1. Create the empty set Q, which will contain an extended set of queries.

No abstract

This research looks at the complexity inherent in the causal relation and the implications for its representation in a Terminological Knowledge Base (TKB). Supported by a more general study of semantic relation hierarchies, a hierarchical refinement of the causal relation is proposed. It results from a manual search of a corpus which shows that it efficiently captures and formalizes variations expressed in text. The feasibility of determining such categorization during automatic extraction from corpora is also explored. Conceptual graphs are used as a representation formalism to which we have added certainty information to capture the degree of certainty surrounding the interaction between two terms involved in a causal relation.

Our work investigates the causal relation as it is expressed in informative texts. We view causal relations as important because of the dynamic dimension they bring to a domain model. Thorough study of a corpus leads us to distinguish two prominent classes of indicators of the causal relation: conjunctional phrases, and verbs. This paper identifies multiple knowledge-rich patterns within each class and studies their usage, frequency and noise. Results from this manual investigation informs a discussion on the feasibility of automatic extraction of the different forms of expression of the causal relation.

No abstract