The CLASSLA-Stanza model for lemmatisation of standard Bulgarian 2.1

  Avtorji

Terčon, Luka ; Ljubešić, Nikola ; Osenova, Petya and Simov, Kiril

  Identifikator vnosa

http://hdl.handle.net/11356/1850

 URL projekta

https://github.com/clarinsi/classla

 Dokumentirano v

http://dx.doi.org/10.18653/v1/W19-3704

 Datum objave

2023-06-27

 Vrsta

toolService

 Jezik(i)

Bulgarian

 Opis

The model for lemmatisation of standard Bulgarian was built with the CLASSLA-Stanza tool (https://github.com/clarinsi/classla) by training on the BulTreeBank training corpus (https://clarino.uib.no/korpuskel/corpora) and using the Bulgarian inflectional lexicon (Popov, Simov, and Vidinska 1998). The estimated F1 of the lemma annotations is ~98.93. The difference to the previous version of the lemmatizer is that this version was trained using the new version of the Bulgarian word embeddings.

 Izdajatelj

Jožef Stefan Institute

 

IICT-BAS

 Zahvala

ARRS (Slovenian Research Agency) P6-0411 "Language Resources and Technologies for Slovene"

Ministry of Education and Science Republic of Bulgaria DO01-272/16.12.2019 "Bulgarian National Interdisciplinary Research e-Infrastructure for Resources and Technologies CLaDA-BG"

Jožef Stefan Institute CLARIN "CLARIN.SI"

ARRS (Slovenian Research Agency) J7-4642 "MEZZANINE"

Connecting Europe Facility (CEF) Telecom INEA/CEF/ICT/A2020/2278341 "MaCoCu - Massive collection and curation of monolingual and bilingual data: focus on under-resourced languages"

 Ključne besede

lemmatisation language model

 Zbirke

CLARIN.SI data & tools

 Druge različice

Seznam vseh različic  

Prikaži polni zapis vnosa