SPINDLE: Spinning Raw Text into Lambda Terms with Graph Attention
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 10 of its 22 references that are in the map. First posted on arXiv 23 Feb 2023.
Builds on
10 of 22 references.
References · 10
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
- 2018Learning Latent Permutations with Gumbel-Sinkhorn Networkscited by 172
- 2017LangPro: Natural Language Theorem Provercited by 15
- 2020Supertagging the Long Tail with Tree-Structured Decoding of Complex Categoriescited by 11
- 2020Neural Proof Netscited by 8
- 2021Something Old, Something New: Grammar-based CCG Parsing with Transformer Modelscited by 6
- 2019Constructive Type-Logical Supertagging with Self-Attention Networkscited by 5
- 2019AE THEL: Automatically Extracted Typelogical Derivations for Dutchcited by 5
- 2022Geometry-Aware Supertagging with Heterogeneous Dynamic Convolutionscited by 3
- 2018Static and Dynamic Vector Semantics for Lambda Calculus Models of Natural Languagecited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.