4 papers · 1 filter
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…
Montague semantics and modifier consistency measurement in neural language models
Danilo S. Carvalho, Edoardo Manino, Julia Rozanova +2
This work proposes a novel methodology for measuring compositional behavior in contemporary language embedding models. Specifically, we focus on adjectival modifier phenomena in ad…
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…
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…