Comparison of Czech Transformers on Text Classification Tasks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F21%3A43962816" target="_blank" >RIV/49777513:23520/21:43962816 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-030-89579-2_3" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-030-89579-2_3</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-89579-2_3" target="_blank" >10.1007/978-3-030-89579-2_3</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Comparison of Czech Transformers on Text Classification Tasks

Popis výsledku v původním jazyce

In this paper, we present our progress in pre-training monolingual Transformers for Czech and contribute to the research community by releasing our models for public. The need for such models emerged from our effort to employ Transformers in our language-specific tasks, but we found the performance of the published multilingual models to be very limited. Since the multilingual models are usually pre-trained from 100+ languages, most of low-resourced languages (including Czech) are under-represented in these models. At the same time, there is a huge amount of monolingual training data available in web archives like Common Crawl. We have pre-trained and publicly released two monolingual Czech Transformers and compared them with relevant public models, trained (at least partially) for Czech. The paper presents the Transformers pre-training procedure as well as a comparison of pre-trained models on text classification task from various domains.

Název v anglickém jazyce

Comparison of Czech Transformers on Text Classification Tasks

Popis výsledku anglicky

In this paper, we present our progress in pre-training monolingual Transformers for Czech and contribute to the research community by releasing our models for public. The need for such models emerged from our effort to employ Transformers in our language-specific tasks, but we found the performance of the published multilingual models to be very limited. Since the multilingual models are usually pre-trained from 100+ languages, most of low-resourced languages (including Czech) are under-represented in these models. At the same time, there is a huge amount of monolingual training data available in web archives like Common Crawl. We have pre-trained and publicly released two monolingual Czech Transformers and compared them with relevant public models, trained (at least partially) for Czech. The paper presents the Transformers pre-training procedure as well as a comparison of pre-trained models on text classification task from various domains.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/DG18P02OVV016" target="_blank" >DG18P02OVV016: Vývoj centralizovaného rozhraní pro vytěžování velkých dat z webových archivů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Statistical Language and Speech Processing, SLSP 2021

ISBN

978-3-030-89578-5

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

11

Strana od-do

27-37

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Cardiff, UK

Datum konání akce

23. 11. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—