Annotation of Czech Texts with Language Mixing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F16%3A00091344" target="_blank" >RIV/00216224:14330/16:00091344 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-45510-5_32" target="_blank" >http://dx.doi.org/10.1007/978-3-319-45510-5_32</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-45510-5_32" target="_blank" >10.1007/978-3-319-45510-5_32</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Annotation of Czech Texts with Language Mixing

Popis výsledku v původním jazyce

Language mixing (using chunks of foreign language in a native language utterance) occurs frequently. Foreign language chunks have to be detected because their annotation is often incorrect. In the standard pipelines of Czech texts annotation, no such detection exists. Before morphological disambiguation, unrecognized words are processed by Czech guesser which is successful on Czech words (e.g. neologisms, typos) but its usage makes no sense on foreign words. We propose a new pipeline that adds foreign language chunk and multi-word expression (MWE) detection. We experimented with a small corpus where we compared the original (semi-automatic) annotation (including foreign words and MWEs) with the results of the new pipelines. As a result, we reduced the number of incorrect annotations of interlingual homographs and foreign language chunks in the new pipeline compared to the standard one. We also reduced the number of tokens that have to be processed by the guesser.

Název v anglickém jazyce

Annotation of Czech Texts with Language Mixing

Popis výsledku anglicky

Language mixing (using chunks of foreign language in a native language utterance) occurs frequently. Foreign language chunks have to be detected because their annotation is often incorrect. In the standard pipelines of Czech texts annotation, no such detection exists. Before morphological disambiguation, unrecognized words are processed by Czech guesser which is successful on Czech words (e.g. neologisms, typos) but its usage makes no sense on foreign words. We propose a new pipeline that adds foreign language chunk and multi-word expression (MWE) detection. We experimented with a small corpus where we compared the original (semi-automatic) annotation (including foreign words and MWEs) with the results of the new pipelines. As a result, we reduced the number of incorrect annotations of interlingual homographs and foreign language chunks in the new pipeline compared to the standard one. We also reduced the number of tokens that have to be processed by the guesser.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

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

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

Text, Speech, and Dialogue 19th International Conference, TSD 2016 Brno, Czech Republic, September 12–16, 2016 Proceedings

ISBN

9783319455099

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

8

Strana od-do

279-286

Název nakladatele

Springer International Publishing

Místo vydání

Switzerland

Místo konání akce

Switzerland

Datum konání akce

1. 1. 2016

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—