SPINDLE: Spinning Raw Text into Lambda Terms with Graph Attention - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier
Communication Dans Un Congrès Année : 2023

SPINDLE: Spinning Raw Text into Lambda Terms with Graph Attention

Résumé

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.
Fichier principal
Vignette du fichier
eacl2023.pdf (265.26 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

lirmm-04290161 , version 1 (16-11-2023)

Licence

Identifiants

Citer

Konstantinos Kogkalidis, Michael Moortgat, Richard Moot. SPINDLE: Spinning Raw Text into Lambda Terms with Graph Attention. EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, May 2023, Dubrovnic, Croatia. pp.128-135, ⟨10.48550/arXiv.2302.12050⟩. ⟨lirmm-04290161⟩
36 Consultations
9 Téléchargements

Altmetric

Partager

More