Bidirectional Long-Short Term Memory tagger

A toolkit for Part-of-Speech tagging and NER in DyNet. It has been tested on Danish, amongst other languages (for the UD POS tags in the UD_Danish-DDT version 1.1 and 2.3)

Status: freely available since 2016,

References:

Plank, Søgaard, Goldberg 2016. Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss. In ACL.

Plank and Klerke, 2019. Lexical Resources for Low-Resource PoS Tagging in Neural Times In NoDaLiDa

Yderligere info

Felt	Værdi
Destinationsside	https://github.com/bplank/bilstm-aux
Metadata sidst opdateret	marts 30, 2021, 11:10 (UTC)
Metadata oprettet	juni 29, 2020, 13:37 (UTC)
Emne	Sprog og retskrivning Uddannelse, kultur og sport
GUID	https://data.gov.dk/dataset/lang/64bbc342-9649-4f55-970d-8ecf233e91f4
Kontaktemail	bapl@itu.dk
Kontaktnavn	Barbara Plank
Opdateret	2020
Opdateringsfrekvens	IRREG
URI	https://data.gov.dk/dataset/lang/64bbc342-9649-4f55-970d-8ecf233e91f4
Udgivelsesdato	2016
Udgivernavn	ITU
Type	https://data.gov.dk/concept/core/lang-resource-type/Tool
Dokumentation	https://www.aclweb.org/anthology/W19-6103/ https://www.aclweb.org/anthology/P16-2067/
usage	["ordklassifikation", "deep learning"]