DisCoCat for Donkey Sentences
This work addresses a specific challenge in natural language semantics for computational linguistics, but it appears incremental as it builds on existing DisCoCat extensions.
The paper tackled the problem of parsing Geach's Donkey sentences in a compositional distributional model of meaning, resulting in a type-logical syntax with defined relational and vector space semantics.
We demonstrate how to parse Geach's Donkey sentences in a compositional distributional model of meaning. We build on previous work on the DisCoCat (Distributional Compositional Categorical) framework, including extensions that model discourse, determiners, and relative pronouns. We present a type-logical syntax for parsing donkey sentences, for which we define both relational and vector space semantics.