Automatic Identification of Learners' Language Background based on their Writing in Czech

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F13%3A10194613" target="_blank" >RIV/00216208:11320/13:10194613 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Automatic Identification of Learners' Language Background based on their Writing in Czech

Popis výsledku v původním jazyce

The goal of this study is to investigate whether learners' written data in highly inflectional Czech can suggest a consistent set of clues for automatic identification of the learners' L1 background. For our experiments, we use texts written by learnersof Czech, which have been automatically and manually annotated for errors. We define two classes of learners: speakers of Indo-European languages and speakers of non-Indo-European languages. We use an SVM classifier to perform the binary classification.We show that non-content based features perform well on highly inflectional data. In particular, features reflecting errors in orthography are the most useful, yielding about 89% precision and the same recall. A detailed discussion of the best performingfeatures is provided.

Název v anglickém jazyce

Automatic Identification of Learners' Language Background based on their Writing in Czech

Popis výsledku anglicky

The goal of this study is to investigate whether learners' written data in highly inflectional Czech can suggest a consistent set of clues for automatic identification of the learners' L1 background. For our experiments, we use texts written by learnersof Czech, which have been automatically and manually annotated for errors. We define two classes of learners: speakers of Indo-European languages and speakers of non-Indo-European languages. We use an SVM classifier to perform the binary classification.We show that non-content based features perform well on highly inflectional data. In particular, features reflecting errors in orthography are the most useful, yielding about 89% precision and the same recall. A detailed discussion of the best performingfeatures is provided.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/GPP406%2F10%2FP328" target="_blank" >GPP406/10/P328: Morfologická analýza a tagging s minimálními zdroji</a><br>

Návaznosti

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

Rok uplatnění

2013

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 6th International Joint Conference on Natural Language Processing

ISBN

978-4-9907348-0-0

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

1428-1436

Název nakladatele

Asian Federation of Natural Language Processing

Místo vydání

Nagoya, Japan

Místo konání akce

Nagoya, Japan

Datum konání akce

14. 10. 2013

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—