Induction, Training, and Parsing Strategies beyond Context-free Grammars

Kilian Gebhardt

AutorIn

Kilian Gebhardt

Titel

Induction, Training, and Parsing Strategies beyond Context-free Grammars

Zitierfähige Url:

https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-713985

Datum der Einreichung

28.11.2019

Datum der Verteidigung

06.05.2020

Abstract (EN)

This thesis considers the problem of assigning a sentence its syntactic structure, which may be discontinuous. It proposes a class of models based on probabilistic grammars that are obtained by the automatic refinement of a given grammar. Different strategies for parsing with a refined grammar are developed. The induction, refinement, and application of two types of grammars (linear context-free rewriting systems and hybrid grammars) are evaluated empirically on two German and one Dutch corpus.

Verweis

Hybrid Grammars for Parsing of Discontinuous Phrase Structures and Non-Projective Dependency Structures
Zugrundeliegender Journal-Artikel
Link: https://www.aclweb.org/anthology/J17-3001
DOI: 10.1162/COLI_a_00291

Generic refinement of expressive grammar formalisms with an application to discontinuous constituent parsing
Zugrundeliegender Konferenzbeitrag
Link: https://www.aclweb.org/anthology/C18-1258

EM-Training for Weighted Aligned Hypergraph Bimorphisms
Zugrundeliegender Tagungsbeitrag
Link: https://www.aclweb.org/anthology/W16-2407
DOI: 10.18653/v1/W16-2407

Advances in Using Grammars with Latent Annotations for Discontinuous Parsing
Ergänzender Tagungsbeitrag
Link: https://www.aclweb.org/anthology/2020.iwpt-1.9

Panda Parser
Software die im Rahmen des Dissertationsprojekts entwickelt wurde
Link: https://www.aclweb.org/anthology/J17-3001

Freie Schlagwörter (DE)

Hybridgrammatiken, Diskontinuierliches Parsing, Syntaktisches Parsing

Freie Schlagwörter (EN)

discontinuous parsing, latent variable grammar, interpreted regular tree grammar, hybrid grammar, linear context-free rewriting system, syntactic parsing

Klassifikation (DDC)