2 code implementations • COLING 2020 • Aikaterini-Lida Kalouli, Richard Crouch, Valeria de Paiva
Despite the advances in Natural Language Inference through the training of massive deep models, recent work has revealed the generalization difficulties of such models, which fail to perform on adversarial datasets with challenging linguistic phenomena.
no code implementations • COLING 2020 • Aikaterini-Lida Kalouli, Rita Sevastjanova, Valeria de Paiva, Richard Crouch, Mennatallah El-Assady
Advances in Natural Language Inference (NLI) have helped us understand what state-of-the-art models really learn and what their generalization power is.
1 code implementation • WS 2019 • Aikaterini-Lida Kalouli, Richard Crouch, Valeria de Paiva
This work focuses on an example of the third and less studied approach: it extends the Graphical Knowledge Representation (GKR) to include distributional features and proposes a division of semantic labour between the distributional and structural/symbolic features.
no code implementations • WS 2019 • Aikaterini-Lida Kalouli, Valeria de Paiva, Richard Crouch
First, we propose that the semantic and not the syntactic contribution of each component of a noun phrase should be considered, so that the resulting composed vectors express more of the phrase meaning.
no code implementations • WS 2018 • Aikaterini-Lida Kalouli, Richard Crouch
This paper describes the first version of an open-source semantic parser that creates graphical representations of sentences to be used for further semantic processing, e. g. for natural language inference, reasoning and semantic similarity.
no code implementations • SEMEVAL 2018 • Richard Crouch, Aikaterini-Lida Kalouli
A position paper arguing that purely graphical representations for natural language semantics lack a fundamental degree of expressiveness, and cannot deal with even basic Boolean operations like negation or disjunction.