Error Classifier (Icelandic Error Corpus categories) for Tokens (22.05)

  Authors

Ingólfsdóttir, Svanhvít Lilja and Snæbjarnarson, Vésteinn

  Item identifier

http://hdl.handle.net/20.500.12537/217

 Date issued

2022-05-31

 Type

toolService

 Language(s)

Icelandic

 Description

 

The Icelandic Error Corpus (http://hdl.handle.net/20.500.12537/73) was used to fine tune the Icelandic language model IceBERT-xlmr-ic3 for token classification. The objective was to train grammatical error detection models that could classify whether a token range contains a particular error type. The model can mark tokens as including one of the following issue categories: coherence, grammar, orthography, other, style and vocabulary. The overall F1 score is 71 and for individual categories as follows: coherence: 0; grammar: 63; orthography: 86; other: 0; vocabulary: 15.2.

 

Íslenska villumálheildin (http://hdl.handle.net/20.500.12537/73) var notuð til að fínþjálfa íslenska mállíkanið IceBERT-xlmr-ic3 fyrir flokkun á tókum/orðum. Markmiðið var að þjálfa líkan sem getur greint hvort orð innihaldi ákveðna villutegund. Líkanið getur merkt við orð með einu af eftirfarandi mörkum: coherence, grammar, orthography, other, style og vocabulary. F1 yfir heildina er 71.

 

 Publisher

Miðeind ehf

 Acknowledgement

Ministry of Education, Science and Culture

Project code: Spell and grammar checking with neural networks (L14)

Project name: Language Technology for Icelandic 2019-2023

 Subject(s)

ged grammatical error detection

 Collection(s)

Clarin IS

Show full item record