Agentività e telicità in GilBERTo: implicazioni cognitive
This work addresses the problem of evaluating neural language models' understanding of semantic properties for researchers in computational linguistics and cognitive science, but it is incremental as it applies existing methods to new linguistic tasks.
The study investigated whether a Transformer-based language model infers lexical semantics like telicity and agentivity to complete morphosyntactic patterns, comparing its performance with Italian native speakers to assess how well the model captures human semantic competence.
The goal of this study is to investigate whether a Transformer-based neural language model infers lexical semantics and use this information for the completion of morphosyntactic patterns. The semantic properties considered are telicity (also combined with definiteness) and agentivity. Both act at the interface between semantics and morphosyntax: they are semantically determined and syntactically encoded. The tasks were submitted to both the computational model and a group of Italian native speakers. The comparison between the two groups of data allows us to investigate to what extent neural language models capture significant aspects of human semantic competence.