Czech Grammar Agreement Dataset for Evaluation of Language Models

PID

AGREE is a dataset and task for evaluation of language models based on grammar agreement in Czech. The dataset consists of sentences with marked suffixes of past tense verbs. The task is to choose the right verb suffix which depends on gender, number and animacy of subject. It is challenging for language models because 1) Czech is morphologically rich, 2) it has relatively free word order, 3) high out-of-vocabulary (OOV) ratio, 4) predicate and subject can be far from each other, 5) subjects can be unexpressed and 6) various semantic rules may apply. The task provides a straightforward and easily reproducible way of evaluating language models on a morphologically rich language.

Identifier
PID http://hdl.handle.net/11234/1-1933
Related Identifier https://www.muni.cz/vyzkum/publikace/1362555
Metadata Access http://lindat.mff.cuni.cz/repository/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:lindat.mff.cuni.cz:11234/1-1933
Provenance
Creator Baisa, Vít
Publisher Masaryk University, NLP Centre
Publication Year 2016
Rights Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0); http://creativecommons.org/licenses/by-sa/4.0/; PUB
OpenAccess true
Contact lindat-help(at)ufal.mff.cuni.cz
Representation
Language Czech
Resource Type corpus
Format text/plain; charset=utf-8; application/x-gzip; downloadable_files_count: 1
Discipline Linguistics