2 papers
cs.CL2021
Representing Syntax and Composition with Geometric Transformations
Lorenzo Bertolini, Julie Weeds, David Weir +1
The exploitation of syntactic graphs (SyGs) as a word's context has been shown to be beneficial for distributional semantic models (DSMs), both at the level of individual word repr…
cs.CL2020
Data Augmentation for Hypernymy Detection
Thomas Kober, Julie Weeds, Lorenzo Bertolini +1
The automatic detection of hypernymy relationships represents a challenging problem in NLP. The successful application of state-of-the-art supervised approaches using distributed r…