Automatic evaluation of surface coherence in L2 texts in Czech

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F16%3A10335521" target="_blank" >RIV/00216208:11320/16:10335521 - isvavai.cz</a>

Výsledek na webu

<a href="http://aclweb.org/anthology/O/O16/O16-1021.pdf" target="_blank" >http://aclweb.org/anthology/O/O16/O16-1021.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Automatic evaluation of surface coherence in L2 texts in Czech

Popis výsledku v původním jazyce

We introduce possibilities of automatic evaluation of surface text coherence (cohesion) in texts written by learners of Czech during certified exams for non-native speakers. On the basis of a corpus analysis, we focus on finding and describing relevant distinctive features for automatic detection of A1-C1 levels (established by CEFR - the Common European Framework of Reference for Languages) in terms of surface text coherence. The CEFR levels are evaluated by human assessors and we try to reach this assessment automatically by using several discourse features like frequency and diversity of discourse connectives, density of discourse relations etc. We present experiments with various features using two machine learning algorithms. Our results of automatic evaluation of CEFR coherence/cohesion marks (compared to human assessment) achieved 73.2% success rate for the detection of A1-C1 levels and 74.9% for the detection of A2-B2 levels.

Název v anglickém jazyce

Automatic evaluation of surface coherence in L2 texts in Czech

Popis výsledku anglicky

We introduce possibilities of automatic evaluation of surface text coherence (cohesion) in texts written by learners of Czech during certified exams for non-native speakers. On the basis of a corpus analysis, we focus on finding and describing relevant distinctive features for automatic detection of A1-C1 levels (established by CEFR - the Common European Framework of Reference for Languages) in terms of surface text coherence. The CEFR levels are evaluated by human assessors and we try to reach this assessment automatically by using several discourse features like frequency and diversity of discourse connectives, density of discourse relations etc. We present experiments with various features using two machine learning algorithms. Our results of automatic evaluation of CEFR coherence/cohesion marks (compared to human assessment) achieved 73.2% success rate for the detection of A1-C1 levels and 74.9% for the detection of A2-B2 levels.

Druh

D - Stať ve sborníku

CEP obor

AM - Pedagogika a školství

OECD FORD obor

—

Projekt

<a href="/cs/project/DG16P02B016" target="_blank" >DG16P02B016: Automatické vyhodnocování koherence textu v češtině</a><br>

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

Proceedings of the 28th Conference on Computational Linguistics and Speech Processing ROCLING XXVIII (2016)

ISBN

978-957-30792-9-3

ISSN

—

e-ISSN

—

Počet stran výsledku

15

Strana od-do

214-228

Název nakladatele

The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)

Místo vydání

Taipei, Taiwan

Místo konání akce

Tainan, Taiwan

Datum konání akce

6. 10. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—