Splitting and Identifying Czech Compounds: A Pilot Study

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440580" target="_blank" >RIV/00216208:11320/21:10440580 - isvavai.cz</a>

Výsledek na webu

<a href="http://nabil.hathout.free.fr/DeriMo2021/pdf-files/DeriMo_2021_paper_14.pdf" target="_blank" >http://nabil.hathout.free.fr/DeriMo2021/pdf-files/DeriMo_2021_paper_14.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Splitting and Identifying Czech Compounds: A Pilot Study

Popis výsledku v původním jazyce

We present pilot experiments on splitting and identifying Czech compound words. We created an algorithm measuring the linguistic similarity of two words based on finding the shortest path through a matrix of mutual estimated correspondences between two phonemic strings. Additionally, a neural compound-splitting tool (Czech Compound Splitter) was implemented by using the Marian Neural Machine Translator framework, which was trained on a data set containing 1,164 hand-annotated compounds and about 280,000 synthetically created compounds. In compound splitting, the first solution achieved an accuracy of 28% and the second solution achieved 54% on a separate validation data set. In compound identification, the Czech Compound Splitter achieved an accuracy of 91%.

Název v anglickém jazyce

Splitting and Identifying Czech Compounds: A Pilot Study

Popis výsledku anglicky

We present pilot experiments on splitting and identifying Czech compound words. We created an algorithm measuring the linguistic similarity of two words based on finding the shortest path through a matrix of mutual estimated correspondences between two phonemic strings. Additionally, a neural compound-splitting tool (Czech Compound Splitter) was implemented by using the Marian Neural Machine Translator framework, which was trained on a data set containing 1,164 hand-annotated compounds and about 280,000 synthetically created compounds. In compound splitting, the first solution achieved an accuracy of 28% and the second solution achieved 54% on a separate validation data set. In compound identification, the Czech Compound Splitter achieved an accuracy of 91%.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

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

Proceedings of the Third International Workshop on Resources and Tools for Derivational Morphology (DeriMo 2021)

ISBN

978-2-9580006-0-8

ISSN

—

e-ISSN

—

Počet stran výsledku

10

Strana od-do

129-138

Název nakladatele

ATILF

Místo vydání

Nancy, France

Místo konání akce

Online

Datum konání akce

9. 9. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—