Grotoco@SLAM: Second Language Acquisition Modeling with Simple Features, Learners and Task-wise Models

Sigrid Klerke; Héctor  Martínez Alonso; Barbara Plank

doi:10.18653/v1/W18-0523

Grotoco@SLAM: Second Language Acquisition Modeling with Simple Features, Learners and Task-wise Models

Sigrid Klerke, Héctor Martínez Alonso, Barbara Plank

Thomson Reuters

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

We present our submission to the 2018 Duolingo Shared Task on Second Language
Acquisition Modeling (SLAM). We focus on evaluating a range of features for the task, including user-derived measures, while examining how far we can get with a simple linear classifier. Our analysis reveals that errors differ per exercise format, which motivates our final and best-performing system: a task-wise (per exercise-format) model.

Original language	English
Title of host publication	Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications : NAACL HLT 2018
Place of Publication	New Orleans
Publisher	Association for Computational Linguistics
Publication date	2018
Pages	206-211
ISBN (Print)	978-1-948087-11-7
DOIs	https://doi.org/10.18653/v1/W18-0523
Publication status	Published - 2018

Keywords

Second Language Acquisition
SLAM
Linear Classifier
Exercise Format
User-Derived Measures

Access to Document

10.18653/v1/W18-0523

sharedtask-duolingo-2018Accepted author manuscript, 675 KB

Cite this

Klerke, S., Martínez Alonso, H., & Plank, B. (2018). Grotoco@SLAM: Second Language Acquisition Modeling with Simple Features, Learners and Task-wise Models. In Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications: NAACL HLT 2018 (pp. 206-211). Association for Computational Linguistics. https://doi.org/10.18653/v1/W18-0523

@inproceedings{87f2f9241a7f4d15ada15c1483da5462,

title = "Grotoco@SLAM: Second Language Acquisition Modeling with Simple Features, Learners and Task-wise Models",

abstract = "We present our submission to the 2018 Duolingo Shared Task on Second LanguageAcquisition Modeling (SLAM). We focus on evaluating a range of features for the task, including user-derived measures, while examining how far we can get with a simple linear classifier. Our analysis reveals that errors differ per exercise format, which motivates our final and best-performing system: a task-wise (per exercise-format) model.",

keywords = "Second Language Acquisition, SLAM, Linear Classifier, Exercise Format, User-Derived Measures, Second Language Acquisition, SLAM, Linear Classifier, Exercise Format, User-Derived Measures",

author = "Sigrid Klerke and {Mart{\'i}nez Alonso}, H{\'e}ctor and Barbara Plank",

year = "2018",

doi = "10.18653/v1/W18-0523",

language = "English",

isbn = "978-1-948087-11-7",

pages = "206--211",

booktitle = "Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications",

publisher = "Association for Computational Linguistics",

address = "United States",

}

Klerke, S, Martínez Alonso, H & Plank, B 2018, Grotoco@SLAM: Second Language Acquisition Modeling with Simple Features, Learners and Task-wise Models. in Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications: NAACL HLT 2018. Association for Computational Linguistics, New Orleans, pp. 206-211. https://doi.org/10.18653/v1/W18-0523

Grotoco@SLAM: Second Language Acquisition Modeling with Simple Features, Learners and Task-wise Models. / Klerke, Sigrid; Martínez Alonso, Héctor ; Plank, Barbara.
Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications: NAACL HLT 2018. New Orleans: Association for Computational Linguistics, 2018. p. 206-211.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - Grotoco@SLAM: Second Language Acquisition Modeling with Simple Features, Learners and Task-wise Models

AU - Klerke, Sigrid

AU - Martínez Alonso, Héctor

AU - Plank, Barbara

PY - 2018

Y1 - 2018

N2 - We present our submission to the 2018 Duolingo Shared Task on Second LanguageAcquisition Modeling (SLAM). We focus on evaluating a range of features for the task, including user-derived measures, while examining how far we can get with a simple linear classifier. Our analysis reveals that errors differ per exercise format, which motivates our final and best-performing system: a task-wise (per exercise-format) model.

AB - We present our submission to the 2018 Duolingo Shared Task on Second LanguageAcquisition Modeling (SLAM). We focus on evaluating a range of features for the task, including user-derived measures, while examining how far we can get with a simple linear classifier. Our analysis reveals that errors differ per exercise format, which motivates our final and best-performing system: a task-wise (per exercise-format) model.

KW - Second Language Acquisition

KW - SLAM

KW - Linear Classifier

KW - Exercise Format

KW - User-Derived Measures

KW - Second Language Acquisition

KW - SLAM

KW - Linear Classifier

KW - Exercise Format

KW - User-Derived Measures

U2 - 10.18653/v1/W18-0523

DO - 10.18653/v1/W18-0523

M3 - Article in proceedings

SN - 978-1-948087-11-7

SP - 206

EP - 211

BT - Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications

PB - Association for Computational Linguistics

CY - New Orleans

ER -

Grotoco@SLAM: Second Language Acquisition Modeling with Simple Features, Learners and Task-wise Models

Abstract

Keywords

Access to Document

Fingerprint

Cite this