Deductive Parsing with an Unbounded Type Lexicon - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier
Conference Papers Year : 2019

Deductive Parsing with an Unbounded Type Lexicon

Abstract

We present a novel deductive parsing framework for categorial type logics, mo-deled as the composition of two components. The first is an attention-based neural supertagger, which assigns words dependency-decorated, contextually informed linear types. It requires no predefined type lexicon, instead utilizing the type syntax to construct types inductively, enabling the use of a richer and more precise typing environment. The type annotations produced are used by the second component, a computationally efficient hybrid system that emulates the inference process of the type logic, iteratively producing a bottom-up reconstruction of the input's derivation-proof and the associated program for compositional meaning assembly. Initial experiments yield promising results for each of the components.
Fichier principal
Vignette du fichier
SEMSPACE2019_paper_4.pdf (180.73 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

lirmm-02313572 , version 1 (11-10-2019)

Identifiers

  • HAL Id : lirmm-02313572 , version 1

Cite

Konstantinos Kogkalidis, Michael Moortgat, Richard Moot, Giorgos Tziafas. Deductive Parsing with an Unbounded Type Lexicon. SemSpace 2019 - 3rd Workshop on Semantic Spaces at the Intersection of NLP, Physics, and Cognitive Science@ESSLLI 2019, Aug 2019, Riga, Latvia. ⟨lirmm-02313572⟩
140 View
135 Download

Share

More