SPINDLE: Spinning Raw Text into Lambda Terms with Graph Attention
This provides a domain-specific tool for computational linguistics and natural language processing researchers working on Dutch language parsing and semantic analysis.
The paper introduces SPINDLE, an open-source Python module that parses raw Dutch text into λ-term programs for meaning composition using a multimodal type-logical grammar, achieving efficient and accurate results through integrated systems like a graph convolution-based supertagger and parallel proof search.
This paper describes SPINDLE - an open source Python module implementing an efficient and accurate parser for written Dutch that transforms raw text input to programs for meaning composition, expressed as λ terms. The parser integrates a number of breakthrough advances made in recent years. Its output consists of hi-res derivations of a multimodal type-logical grammar, capturing two orthogonal axes of syntax, namely deep function-argument structures and dependency relations. These are produced by three interdependent systems: a static type-checker asserting the well-formedness of grammatical analyses, a state-of-the-art, structurally-aware supertagger based on heterogeneous graph convolutions, and a massively parallel proof search component based on Sinkhorn iterations. Packed in the software are also handy utilities and extras for proof visualization and inference, intended to facilitate end-user utilization.