Neural Rerankers for Dependency Parsing

Dataset

DOI

This resource contains code for different types of neural rerankers (RCNN, RCNN-shared and GCN) from the paper: Do and Rehbein (2020). "Neural Reranking for Dependency Parsing: An Evaluation". We also include in this resource the pre-trained models of different rerankers on 3 languages: English, German and Czech that are used to report results in the paper.

Identifier
DOI	https://doi.org/10.11588/data/NNGPQZ
Related Identifier	https://doi.org/10.18653/v1/2020.acl-main.379
Metadata Access	https://heidata.uni-heidelberg.de/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=doi:10.11588/data/NNGPQZ

Provenance
Creator	Do, Bich-Ngoc; Rehbein, Ines
Publisher	heiDATA
Contributor	Do, Bich-Ngoc
Publication Year	2023
Rights	info:eu-repo/semantics/openAccess
OpenAccess	true
Contact	Do, Bich-Ngoc (Institute of Computational Linguistics, Heidelberg University & Leibniz Institute for German Language)

Representation
Resource Type	source code; Dataset
Format	application/gzip; application/zip; text/markdown
Size	67611294; 60858042; 76156535; 38302104; 97594841; 24957801; 18619960; 119236226; 93481; 1576; 82; 577
Version	1.0
Discipline	Humanities