Skip to Main content Skip to Navigation
Conference papers

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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-02313572
Contributor : Richard Moot <>
Submitted on : Friday, October 11, 2019 - 1:40:58 PM
Last modification on : Saturday, October 12, 2019 - 1:22:46 AM

File

SEMSPACE2019_paper_4.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : lirmm-02313572, version 1

Collections

Citation

Konstantinos Kogkalidis, Michael Moortgat, Richard Moot, Giorgos Tziafas. Deductive Parsing with an Unbounded Type Lexicon. SEMSPACE, Aug 2019, Riga, Latvia. ⟨lirmm-02313572⟩

Share

Metrics

Record views

105

Files downloads

75