A Dataset and Strong Baselines for Classification of Czech News Texts

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475727" target="_blank" >RIV/00216208:11320/23:10475727 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1007/978-3-031-40498-6_4" target="_blank" >https://doi.org/10.1007/978-3-031-40498-6_4</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-40498-6_4" target="_blank" >10.1007/978-3-031-40498-6_4</a>

Result language

angličtina

Original language name

A Dataset and Strong Baselines for Classification of Czech News Texts

Original language description

Pre-trained models for Czech Natural Language Processing are often evaluated on purely linguistic tasks (POS tagging, parsing, NER) and relatively simple classification tasks such as sentiment classification or article classification from a single news source. As an alternative, we present CZEch NEws Classification dataset (CZE-NEC), one of the largest Czech classification datasets, composed of news articles from various sources spanning over twenty years, which allows a more rigorous evaluation of such models. We define four classification tasks: news source, news category, inferred author&apos;s gender, and day of the week. To verify the task difficulty, we conducted a human evaluation, which revealed that human performance lags behind strong machine-learning baselines built upon pre-trained transformer models. Furthermore, we show that language-specific pre-trained encoder analysis outperforms selected commercially available large-scale generative language models.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2023

Confidentiality

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

Article name in the collection

Lecture Notes in Artificial Intelligence

ISBN

978-3-031-40497-9

ISSN

—

e-ISSN

1611-3349

Number of pages

12

Pages from-to

33-44

Publisher name

Springer

Place of publication

Cham, Switzerland

Event location

Plzeň, Czechia

Event date

Sep 4, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—