CUNI System for the Building Educational Applications 2019 Shared Task: Grammatical Error Correction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10405589" target="_blank" >RIV/00216208:11320/19:10405589 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.aclweb.org/anthology/W19-4419/" target="_blank" >https://www.aclweb.org/anthology/W19-4419/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

CUNI System for the Building Educational Applications 2019 Shared Task: Grammatical Error Correction

Popis výsledku v původním jazyce

In this paper, we describe our systems submitted to the Building Educational Applications (BEA) 2019 Shared Task (Bryant et al., 2019). We participated in all three tracks. Our models are NMT systems based on the Transformer model, which we improve by incorporating several enhancements: applying dropout to whole source and target words, weighting target subwords, averaging model checkpoints, and using the trained model iteratively for correcting the intermediate translations. The system in the Restricted Track is trained on the provided corpora with oversampled &quot;cleaner&quot; sentences and reaches 59.39 F0.5 score on the test set. The system in the Low-Resource Track is trained from Wikipedia revision histories and reaches 44.13 F0.5 score. Finally, we finetune the system from the Low-Resource Track on restricted data and achieve 64.55 F0.5 score, placing third in the Unrestricted Track.

Název v anglickém jazyce

CUNI System for the Building Educational Applications 2019 Shared Task: Grammatical Error Correction

Popis výsledku anglicky

In this paper, we describe our systems submitted to the Building Educational Applications (BEA) 2019 Shared Task (Bryant et al., 2019). We participated in all three tracks. Our models are NMT systems based on the Transformer model, which we improve by incorporating several enhancements: applying dropout to whole source and target words, weighting target subwords, averaging model checkpoints, and using the trained model iteratively for correcting the intermediate translations. The system in the Restricted Track is trained on the provided corpora with oversampled &quot;cleaner&quot; sentences and reaches 59.39 F0.5 score on the test set. The system in the Low-Resource Track is trained from Wikipedia revision histories and reaches 44.13 F0.5 score. Finally, we finetune the system from the Low-Resource Track on restricted data and achieve 64.55 F0.5 score, placing third in the Unrestricted Track.

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)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications

ISBN

978-1-950737-34-5

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

183-190

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Firenze, Italy

Datum konání akce

2. 8. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—