Use this url to cite publication: https://cris.mruni.eu/cris/handle/007/46397
Validation of the Bigger Analogy Test Set Translation into Croatian, Lithuanian and Slovak
Type of publication
Straipsnis recenzuojamoje užsienio konferencijos medžiagoje / Article in peer-reviewed foreign conference proceedings (P1g)
Author(s)
| Author | Affiliation | |
|---|---|---|
Garabík, Radovan | ||
Title
Validation of the Bigger Analogy Test Set Translation into Croatian, Lithuanian and Slovak
Publisher
NOVA CLUNL, 2023
Date Issued
| Date | Start Page | End Page |
|---|---|---|
2023 | 402 | 409 |
Extent
p. 402-409
Is part of
Language, Data and Knowledge 2023 (LDK 2023) : Proceedings of the 4th Conference on Language, Data and Knowledge, 12–15 September 2023. Vienna, Austria / ed. Sara Carvalho... [et all.]
Field of Science
Abstract
This paper presents ongoing work focused on the analysis of translations of the English Bigger Analogy Test Set (BATS) dataset into three languages: Croatian, Lithuanian, and Slovak. We describe our automatic validation and further manual correction of the translations and analyse the main types of issues encountered in the dataset. The validation process involves checking the translations against morphological databases in order to uncover obvious mistakes or typos. Additionally, the translations are tested for the compliance to some of the formal guidelines for the Bigger Analogy Test Set translations, and for rudimentary grammatical correctness.
Type of document
text::conference output::conference proceedings::conference paper
ISBN (of the container)
9789895408153
eLABa
180478207
ISBN (of the reviewed item)
9789895408153
Coverage Spatial
Portugalija / Portugal (PT)
Language
Anglų / English (en)
Bibliographic Details
15
Affiliation(s)
Project(s)
COST Action NexusLinguarum - European network for Web-centered linguistic data science (CA18209) |
Date Reporting
2023
Access Rights
Atviroji prieiga / Open Access
File(s)