MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AEEFA87MT" target="_blank" >RIV/00216208:11320/23:EEFA87MT - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85173111233&partnerID=40&md5=5c0453f46c2982ca4051784f208b775f" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85173111233&partnerID=40&md5=5c0453f46c2982ca4051784f208b775f</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages

Popis výsledku v původním jazyce

"In this paper, we present MasakhaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages. We discuss the challenges in annotating POS for these languages using the UD (universal dependencies) guidelines. We conducted extensive POS baseline experiments using conditional random field and several multilingual pretrained language models. We applied various cross-lingual transfer models trained with data available in UD. Evaluating on the MasakhaPOS dataset, we show that choosing the best transfer language(s) in both single-source and multi-source setups greatly improves the POS tagging performance of the target languages, in particular when combined with cross-lingual parameter-efficient fine-tuning methods. Crucially, transferring knowledge from a language that matches the language family and morphosyntactic properties seems more effective for POS tagging in unseen languages. © 2023 Association for Computational Linguistics."

Název v anglickém jazyce

MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages

Popis výsledku anglicky

"In this paper, we present MasakhaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages. We discuss the challenges in annotating POS for these languages using the UD (universal dependencies) guidelines. We conducted extensive POS baseline experiments using conditional random field and several multilingual pretrained language models. We applied various cross-lingual transfer models trained with data available in UD. Evaluating on the MasakhaPOS dataset, we show that choosing the best transfer language(s) in both single-source and multi-source setups greatly improves the POS tagging performance of the target languages, in particular when combined with cross-lingual parameter-efficient fine-tuning methods. Crucially, transferring knowledge from a language that matches the language family and morphosyntactic properties seems more effective for POS tagging in unseen languages. © 2023 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

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

"Proc. Annu. Meet. Assoc. Comput Linguist."

ISBN

978-195942972-2

ISSN

0736-587X

e-ISSN

—

Počet stran výsledku

18

Strana od-do

10883-10900

Název nakladatele

Association for Computational Linguistics (ACL)

Místo vydání

—

Místo konání akce

Dubrovnik

Datum konání akce

1. 1. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—