Combining Formal and Distributional Models of Temporal and Intensional Semantics

Abstract

We outline a vision for computational semantics in which formal compositional semantics is combined with a powerful, structured lexical semantics derived from distributional statistics. We consider how existing work (Lewis and Steedman, 2013) could be extended with a much richer lexical semantics using recent techniques for modelling processes (Scaria et al., 2013)—for example, learning that visiting events start with arriving and end with leaving. We show how to closely integrate this information with theories of formal semantics, allowing complex compositional inferences such as is visiting!has arrived in but will leave, which requires interpreting both the function and content words. This will allow machine reading systems to understand not just what has happened, but when.