Improvements to Korektor: A case study with native and non-native Czech

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F15%3A10318156" target="_blank" >RIV/00216208:11320/15:10318156 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00216208:11210/15:10318156

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Improvements to Korektor: A case study with native and non-native Czech

Popis výsledku v původním jazyce

We present recent developments of Korektor, a statistical spell checking system. In addition to lexicon, Korektor uses language models to find real-word errors, detectable only in context. The models and error probabilities, learned from error corpora, are also used to suggest the most likely corrections. Korektor was originally trained on a small error corpus and used language models extracted from an in-house corpus WebColl. We show two recent improvements: . We built new language models from freely avail- able (shuffled) versions of the Czech National Corpus and show that these perform consistently better on texts produced both by native speakers and non-native learners of Czech. . We trained new error models on a manually annotated learner corpus and show that they perform better than the standard error model (in error detection) not only for the learners' texts, but also for our standard eval- uation data of native Czech. For error correction, the standard error model outperformed

Název v anglickém jazyce

Improvements to Korektor: A case study with native and non-native Czech

Popis výsledku anglicky

We present recent developments of Korektor, a statistical spell checking system. In addition to lexicon, Korektor uses language models to find real-word errors, detectable only in context. The models and error probabilities, learned from error corpora, are also used to suggest the most likely corrections. Korektor was originally trained on a small error corpus and used language models extracted from an in-house corpus WebColl. We show two recent improvements: . We built new language models from freely avail- able (shuffled) versions of the Czech National Corpus and show that these perform consistently better on texts produced both by native speakers and non-native learners of Czech. . We trained new error models on a manually annotated learner corpus and show that they perform better than the standard error model (in error detection) not only for the learners' texts, but also for our standard eval- uation data of native Czech. For error correction, the standard error model outperformed

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

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 15th conference ITAT 2015: Slovenskočeský NLP workshop (SloNLP 2015)

ISBN

978-1-5151-2065-0

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

8

Strana od-do

73-80

Název nakladatele

CreateSpace Independent Publishing Platform

Místo vydání

Praha, Czechia

Místo konání akce

Smižany, Slovakia

Datum konání akce

20. 9. 2015

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—