Adapting transformer models to morphological tagging of two highly inflectional languages: a case study on Ancient Greek and Latin

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AD98VMAQ7" target="_blank" >RIV/00216208:11320/25:D98VMAQ7 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204790433&partnerID=40&md5=4ba3138331d465bd6d4b3e696f6a8bda" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204790433&partnerID=40&md5=4ba3138331d465bd6d4b3e696f6a8bda</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Adapting transformer models to morphological tagging of two highly inflectional languages: a case study on Ancient Greek and Latin

Popis výsledku v původním jazyce

Natural language processing for Greek and Latin, inflectional languages with small corpora, requires special techniques. For morphological tagging, transformer models show promising potential, but the best approach to use these models is unclear. For both languages, this paper examines the impact of using morphological lexica, training different model types (a single model with a combined feature tag, multiple models for separate features, and a multi-task model for all features), and adding linguistic constraints. We find that, although simply fine-tuning transformers to predict a monolithic tag may already yield decent results, each of these adaptations can further improve tagging accuracy. © 2024 Association for Computational Linguistics.

Název v anglickém jazyce

Adapting transformer models to morphological tagging of two highly inflectional languages: a case study on Ancient Greek and Latin

Popis výsledku anglicky

Natural language processing for Greek and Latin, inflectional languages with small corpora, requires special techniques. For morphological tagging, transformer models show promising potential, but the best approach to use these models is unclear. For both languages, this paper examines the impact of using morphological lexica, training different model types (a single model with a combined feature tag, multiple models for separate features, and a multi-task model for all features), and adding linguistic constraints. We find that, although simply fine-tuning transformers to predict a monolithic tag may already yield decent results, each of these adaptations can further improve tagging accuracy. © 2024 Association for Computational Linguistics.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ML4AL - Workshop Mach. Learn. Anc. Lang., Proc. Workshop

ISBN

979-889176144-5

ISSN

—

e-ISSN

—

Počet stran výsledku

12

Strana od-do

165-176

Název nakladatele

Association for Computational Linguistics (ACL)

Místo vydání

—

Místo konání akce

Hybrid, Bangkok

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—