Graph Knowledge Representations for SICK

EasyChair Preprint 217

Abstract

Determining semantic relationships between sentences is essential for machines that understand and reason with natural language. Despite neural networks big successes, end-to-end neural architectures still fail to get acceptable performance for textual inference, maybe due to lack of adequate datasets for learning. Recently large datasets have been constructed e.g. SICK, SNLI, MultiNLI, but it is not clear how trustworthy these datasets are. This paper describes work on an expressive open-source semantic parser GKR that creates graphical representations of sentences used for further semantic processing, e.g. for natural language inference, reasoning and semantic similarity. The GKR is inspired by the Abstract Knowledge Representation (AKR), which separates out conceptual and contextual levels of representation that deal respectively with the subject matter of a sentence and its existential commitments. We recall work investigating SICK and its problematic annotations and propose to use GKR as a better representation for the semantics of SICK sentences.

Keyphrases: Abstract Knowledge Representation, Abstract Meaning Representation, Conceptual Graph, Inference Relation, Natural Language Inference, aikaterini lida kalouli, computational linguistic, knowledge representation, richard crouch, semantic parsing, textual inference

@booklet{EasyChair:217,
  author    = {Aikaterini-Lida Kalouli and Richard Crouch and Valeria de Paiva and Livy Real},
  title     = {Graph Knowledge Representations for SICK},
  doi       = {10.29007/l34q},
  howpublished = {EasyChair Preprint 217},
  year      = {EasyChair, 2018}}