5 papers
Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder
Yingji Zhang, Danilo S. Carvalho, André Freitas
Formal/symbolic semantics can provide canonical, rigid controllability and interpretability to sentence representations due to their \textit{localisation} or \textit{composition} p…
Towards Controllable Natural Language Inference through Lexical Inference Types
Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann +1
Explainable natural language inference aims to provide a mechanism to produce explanatory (abductive) inference chains which ground claims to their supporting premises. A recent co…
The Adjacent Fragment and Quine's Limits of Decision
Bartosz Bednarczyk, Daumantas Kojelis, Ian Pratt-Hartmann
We introduce the adjacent fragment AF of first-order logic, obtained by restricting the sequences of variables occurring as arguments in atomic formulas. The adjacent fragment gene…
Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks
Yingji Zhang, Danilo S. Carvalho, André Freitas
Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While…
Walking on Words
Ian Pratt-Hartmann
Take any word over some alphabet. If it is non-empty, go to any position and print out the letter being scanned. Now repeat the following any number of times (possibly zero): eithe…