Representing Syntax and Composition with Geometric Transformations
This work addresses efficiency and representation issues in natural language processing for researchers, though it is incremental as it adapts existing methods to a new domain.
The paper tackled the problem of high parameter counts and data sparsity in syntactically-aware distributional semantic models by adopting geometric transformations from knowledge graphs to encode syntactic graphs, resulting in improved phrase-level composition with competitive performance on benchmarks.
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 representations and in deriving phrasal representations via composition. However, notwithstanding the potential performance benefit, the syntactically-aware DSMs proposed to date have huge numbers of parameters (compared to conventional DSMs) and suffer from data sparsity. Furthermore, the encoding of the SyG links (i.e., the syntactic relations) has been largely limited to linear maps. The knowledge graphs' literature, on the other hand, has proposed light-weight models employing different geometric transformations (GTs) to encode edges in a knowledge graph (KG). Our work explores the possibility of adopting this family of models to encode SyGs. Furthermore, we investigate which GT better encodes syntactic relations, so that these representations can be used to enhance phrase-level composition via syntactic contextualisation.