News

Aaron White wins NSF support

Congratulations to 2015 alum Aaron White, whose MegaAttitude Project with Kyle Rawlins and Ben Van Durme from Hopkins has won NSF support. The project – which continues work represented in Aaron's UMD dissertation, with advisors Valentine Hacquard and Jeffrey Lidz, on learning attitude verb meanings by syntactic bootstrapping – seeks to understand what inferences can be drawn about the meanings of mental state verbs, based on the syntactic typology of their complement clauses. It does this in two ways. "First, it develops and deploys multiple scalable, crowd-sourced annotation protocols, based on experimental methodologies from psycholinguistics, in order to collect data about a wide variety of inference patterns triggered by all of the thousands of English predicates that combine with subordinate clauses. Second, it leverages recent advances in multi-task machine learning to build a unified computational model of the relationship between such predicates, the structure of their subordinate clauses, and the inferences that they trigger, which is trained on these data. This model not only helps to reveal systematicities in how humans compute the inference patterns of interest; it can also be straightforwardly incorporated into applied technologies for natural language understanding."