Modeling language learning using specialized Elo ratings

Jue Hou, Maximilian Koppatz, Jose María Hoya Quecedo, Nataliya Stoyanova, Mikhail Kopotev, Roman Yangarber

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

Sammanfattning

Automatic assessment of the proficiency levels of the learner is a critical part of Intelligent Tutoring Systems. We present methods for assessment in the context of language learning. We use a specialized Elo formula used in conjunction with educational data mining. We simultaneously obtain ratings for the proficiency of the learners and for the difficulty of the linguistic concepts that the learners are trying to master. From the same data we also learn a graph structure representing a domain model capturing the relations among the concepts. This application of Elo provides ratings for learners and concepts which correlate well with subjective proficiency levels of the learners and difficulty levels of the concepts.
Originalspråkengelska
Titel på gästpublikationInnovative Use of NLP for Building Educational Applications : Proceedings of the 14th Workshop
RedaktörerHelen Yannakoudakis, Ekaterina Kochmar, Claudia Leacock, Nitin Madnani, Ildikó Pilán, Torsten Zesch
Antal sidor13
UtgivningsortStroudsburg
FörlagThe Association for Computational Linguistics
Utgivningsdatumaug 2019
Sidor494-506
ISBN (elektroniskt)978-1-950737-34-5
StatusPublicerad - aug 2019
MoE-publikationstypA4 Artikel i en konferenspublikation
EvenemangWorkshop on Innovative Use of NLP for Building Educational Applications - Florence, Italien
Varaktighet: 2 aug 20192 aug 2019
Konferensnummer: 14

Vetenskapsgrenar

  • 113 Data- och informationsvetenskap
  • 516 Pedagogik
  • 6121 Språkvetenskaper

Citera det här

Hou, J., Koppatz, M., Hoya Quecedo, J. M., Stoyanova, N., Kopotev, M., & Yangarber, R. (2019). Modeling language learning using specialized Elo ratings. I H. Yannakoudakis, E. Kochmar, C. Leacock, N. Madnani, I. Pilán, & T. Zesch (Red.), Innovative Use of NLP for Building Educational Applications: Proceedings of the 14th Workshop (s. 494-506). Stroudsburg: The Association for Computational Linguistics.
Hou, Jue ; Koppatz, Maximilian ; Hoya Quecedo, Jose María ; Stoyanova, Nataliya ; Kopotev, Mikhail ; Yangarber, Roman. / Modeling language learning using specialized Elo ratings. Innovative Use of NLP for Building Educational Applications: Proceedings of the 14th Workshop. redaktör / Helen Yannakoudakis ; Ekaterina Kochmar ; Claudia Leacock ; Nitin Madnani ; Ildikó Pilán ; Torsten Zesch. Stroudsburg : The Association for Computational Linguistics, 2019. s. 494-506
@inproceedings{52dc7c909e77493fa9f21dcee2ec512e,
title = "Modeling language learning using specialized Elo ratings",
abstract = "Automatic assessment of the proficiency levels of the learner is a critical part of Intelligent Tutoring Systems. We present methods for assessment in the context of language learning. We use a specialized Elo formula used in conjunction with educational data mining. We simultaneously obtain ratings for the proficiency of the learners and for the difficulty of the linguistic concepts that the learners are trying to master. From the same data we also learn a graph structure representing a domain model capturing the relations among the concepts. This application of Elo provides ratings for learners and concepts which correlate well with subjective proficiency levels of the learners and difficulty levels of the concepts.",
keywords = "113 Computer and information sciences, 516 Educational sciences, 6121 Languages",
author = "Jue Hou and Maximilian Koppatz and {Hoya Quecedo}, {Jose Mar{\'i}a} and Nataliya Stoyanova and Mikhail Kopotev and Roman Yangarber",
year = "2019",
month = "8",
language = "English",
pages = "494--506",
editor = "Yannakoudakis, {Helen } and Kochmar, {Ekaterina } and Leacock, {Claudia } and Madnani, {Nitin } and Pil{\'a}n, {Ildik{\'o} } and Torsten Zesch",
booktitle = "Innovative Use of NLP for Building Educational Applications",
publisher = "The Association for Computational Linguistics",
address = "United States",

}

Hou, J, Koppatz, M, Hoya Quecedo, JM, Stoyanova, N, Kopotev, M & Yangarber, R 2019, Modeling language learning using specialized Elo ratings. i H Yannakoudakis, E Kochmar, C Leacock, N Madnani, I Pilán & T Zesch (red), Innovative Use of NLP for Building Educational Applications: Proceedings of the 14th Workshop. The Association for Computational Linguistics, Stroudsburg, s. 494-506, Workshop on Innovative Use of NLP for Building Educational Applications , Italien, 02/08/2019.

Modeling language learning using specialized Elo ratings. / Hou, Jue; Koppatz, Maximilian; Hoya Quecedo, Jose María; Stoyanova, Nataliya; Kopotev, Mikhail; Yangarber, Roman.

Innovative Use of NLP for Building Educational Applications: Proceedings of the 14th Workshop. red. / Helen Yannakoudakis; Ekaterina Kochmar; Claudia Leacock; Nitin Madnani; Ildikó Pilán; Torsten Zesch. Stroudsburg : The Association for Computational Linguistics, 2019. s. 494-506.

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

TY - GEN

T1 - Modeling language learning using specialized Elo ratings

AU - Hou, Jue

AU - Koppatz, Maximilian

AU - Hoya Quecedo, Jose María

AU - Stoyanova, Nataliya

AU - Kopotev, Mikhail

AU - Yangarber, Roman

PY - 2019/8

Y1 - 2019/8

N2 - Automatic assessment of the proficiency levels of the learner is a critical part of Intelligent Tutoring Systems. We present methods for assessment in the context of language learning. We use a specialized Elo formula used in conjunction with educational data mining. We simultaneously obtain ratings for the proficiency of the learners and for the difficulty of the linguistic concepts that the learners are trying to master. From the same data we also learn a graph structure representing a domain model capturing the relations among the concepts. This application of Elo provides ratings for learners and concepts which correlate well with subjective proficiency levels of the learners and difficulty levels of the concepts.

AB - Automatic assessment of the proficiency levels of the learner is a critical part of Intelligent Tutoring Systems. We present methods for assessment in the context of language learning. We use a specialized Elo formula used in conjunction with educational data mining. We simultaneously obtain ratings for the proficiency of the learners and for the difficulty of the linguistic concepts that the learners are trying to master. From the same data we also learn a graph structure representing a domain model capturing the relations among the concepts. This application of Elo provides ratings for learners and concepts which correlate well with subjective proficiency levels of the learners and difficulty levels of the concepts.

KW - 113 Computer and information sciences

KW - 516 Educational sciences

KW - 6121 Languages

M3 - Conference contribution

SP - 494

EP - 506

BT - Innovative Use of NLP for Building Educational Applications

A2 - Yannakoudakis, Helen

A2 - Kochmar, Ekaterina

A2 - Leacock, Claudia

A2 - Madnani, Nitin

A2 - Pilán, Ildikó

A2 - Zesch, Torsten

PB - The Association for Computational Linguistics

CY - Stroudsburg

ER -

Hou J, Koppatz M, Hoya Quecedo JM, Stoyanova N, Kopotev M, Yangarber R. Modeling language learning using specialized Elo ratings. I Yannakoudakis H, Kochmar E, Leacock C, Madnani N, Pilán I, Zesch T, redaktörer, Innovative Use of NLP for Building Educational Applications: Proceedings of the 14th Workshop. Stroudsburg: The Association for Computational Linguistics. 2019. s. 494-506