Gao, Lingyu; Gimpel, Kevin; Jensson, Arnar
Distractor Analysis and Selection for Multiple-Choice Cloze Questions for Second-Language Learners Konferenzbeitrag
In: Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, S. 102–114, Association for Computational Linguistics, Seattle, WA, USA (Online), 2020.
Abstract | Links | BibTeX | Schlagwörter: distractor, language learning, Multiple-choice, O, quiz
@inproceedings{Gao2020,
title = {Distractor Analysis and Selection for Multiple-Choice Cloze Questions for Second-Language Learners},
author = {Lingyu Gao and Kevin Gimpel and Arnar Jensson},
url = {https://www.aclweb.org/anthology/2020.bea-1.10},
doi = {10.18653/v1/2020.bea-1.10},
year = {2020},
date = {2020-12-01},
booktitle = {Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications},
pages = {102–114},
publisher = {Association for Computational Linguistics},
address = {Seattle, WA, USA (Online)},
abstract = {We consider the problem of automatically suggesting distractors for multiple-choice cloze questions designed for second-language learners. We describe the creation of a dataset including collecting manual annotations for distractor selection. We assess the relationship between the choices of the annotators and features based on distractors and the correct answers, both with and without the surrounding passage context in the cloze questions. Simple features of the distractor and correct answer correlate with the annotations, though we find substantial benefit to additionally using large-scale pretrained models to measure the fit of the distractor in the context. Based on these analyses, we propose and train models to automatically select distractors, and measure the importance of model components quantitatively.},
keywords = {distractor, language learning, Multiple-choice, O, quiz},
pubstate = {published},
tppubtype = {inproceedings}
}
We consider the problem of automatically suggesting distractors for multiple-choice cloze questions designed for second-language learners. We describe the creation of a dataset including collecting manual annotations for distractor selection. We assess the relationship between the choices of the annotators and features based on distractors and the correct answers, both with and without the surrounding passage context in the cloze questions. Simple features of the distractor and correct answer correlate with the annotations, though we find substantial benefit to additionally using large-scale pretrained models to measure the fit of the distractor in the context. Based on these analyses, we propose and train models to automatically select distractors, and measure the importance of model components quantitatively.
Huynh, Duy; Iida, Hiroyuki
An Analysis of Winning Streak's Effects in Language Course of "Duolingo" Artikel
In: Asia-Pacific Journal of Information Technology and Multimedia, Bd. 6, Nr. 2, S. 23–29, 2017, ISSN: 2289-2192.
Abstract | Links | BibTeX | Schlagwörter: A, Duolingo, game theory, gamification, language learning
@article{Huynh2017,
title = {An Analysis of Winning Streak's Effects in Language Course of "Duolingo"},
author = {Duy Huynh and Hiroyuki Iida},
url = {http://ejournals.ukm.my/apjitm/article/view/18800/7040},
issn = {2289-2192},
year = {2017},
date = {2017-12-01},
urldate = {2018-04-22},
journal = {Asia-Pacific Journal of Information Technology and Multimedia},
volume = {6},
number = {2},
pages = {23--29},
abstract = {This paper explores the effects of the winning streak on users' motivation and engagement in Duolingo's language course. The winning streak has been used in sport and video games to describe a consecutive number of successful actions and increase players' attention to complete their goal. Similarly, in gamified education system, the winning streak is employed as a game element to boost up motivation of learners. By applying game refinement theory as an assessment method, enjoyment of two user groups in Duolingo is measured to compare. The results indicate that the winning streak can boost up learners' motivation and attention to complete their goals. It also expressed that the winning streak is more significant for advanced learners who are in the high level of milestone than those who are in the low level of milestone.},
keywords = {A, Duolingo, game theory, gamification, language learning},
pubstate = {published},
tppubtype = {article}
}
This paper explores the effects of the winning streak on users' motivation and engagement in Duolingo's language course. The winning streak has been used in sport and video games to describe a consecutive number of successful actions and increase players' attention to complete their goal. Similarly, in gamified education system, the winning streak is employed as a game element to boost up motivation of learners. By applying game refinement theory as an assessment method, enjoyment of two user groups in Duolingo is measured to compare. The results indicate that the winning streak can boost up learners' motivation and attention to complete their goals. It also expressed that the winning streak is more significant for advanced learners who are in the high level of milestone than those who are in the low level of milestone.
Finardi, Kyria Rebeca; Leao, Roberta Gomes; Amorim, Gabriel Brito
Mobile Assisted Language Learning: Affordances and Limitations of Duolingo Artikel
In: Education and Linguistics Research, Bd. 2, Nr. 2, 2016, ISSN: 2377-1356.
Abstract | Links | BibTeX | Schlagwörter: A, Duolingo, evaluation, language learning, mobile learning
@article{Finardi2016,
title = {Mobile Assisted Language Learning: Affordances and Limitations of Duolingo},
author = {Kyria Rebeca Finardi and Roberta Gomes Leao and Gabriel Brito Amorim},
url = {https://doi.org/10.5296/elr.v2i2.9842},
doi = {10.5296/elr.v2i2.9842},
issn = {2377-1356},
year = {2016},
date = {2016-09-11},
urldate = {2018-04-22},
journal = {Education and Linguistics Research},
volume = {2},
number = {2},
abstract = {This study aimed at analyzing how mobile assisted language learning (MALL) may be used to aid second/foreign language (L2) learning. So as to reach this goal, the Duolingo platform, one of the most popular apps among L2 learners, was analyzed in terms of its possibilities and limitations for L2 learning as perceived by its users. With that aim, a study was carried out with 80 participants, 45 of whom were L2 learners who answered an online survey about their preferences for L2 learning, 25 MALL users and 10 L2 teachers who were interviewed. Data analysis used a mixed methods design with predominantly qualitative data. Results of the study showed that participants recognize the relevance of MALL for L2 learning and think that the Duolingo may aid L2 learning to a certain extent, but agree that a teacher is necessary to foster interaction and the development of production skills in L2. Based on these results the study concluded that L2 teachers should consider using blended approaches combining MALL in traditional classes.},
keywords = {A, Duolingo, evaluation, language learning, mobile learning},
pubstate = {published},
tppubtype = {article}
}
This study aimed at analyzing how mobile assisted language learning (MALL) may be used to aid second/foreign language (L2) learning. So as to reach this goal, the Duolingo platform, one of the most popular apps among L2 learners, was analyzed in terms of its possibilities and limitations for L2 learning as perceived by its users. With that aim, a study was carried out with 80 participants, 45 of whom were L2 learners who answered an online survey about their preferences for L2 learning, 25 MALL users and 10 L2 teachers who were interviewed. Data analysis used a mixed methods design with predominantly qualitative data. Results of the study showed that participants recognize the relevance of MALL for L2 learning and think that the Duolingo may aid L2 learning to a certain extent, but agree that a teacher is necessary to foster interaction and the development of production skills in L2. Based on these results the study concluded that L2 teachers should consider using blended approaches combining MALL in traditional classes.
Garcia, Ignacio
Learning a Language for Free While Translating the Web. Does Duolingo Work? Artikel
In: International Journal of English Linguistics, Bd. 3, Nr. 1, 2013, ISSN: 1923-8703.
Abstract | Links | BibTeX | Schlagwörter: A, Duolingo, language learning
@article{Garcia2013,
title = {Learning a Language for Free While Translating the Web. Does Duolingo Work?},
author = {Ignacio Garcia},
url = {http://dx.doi.org/10.5539/ijel.v3n1p19},
doi = {10.5539/ijel.v3n1p19},
issn = {1923-8703},
year = {2013},
date = {2013-01-25},
urldate = {2018-04-22},
journal = {International Journal of English Linguistics},
volume = {3},
number = {1},
publisher = {Canadian Center of Science and Education},
abstract = {Duolingo, a free online language learning site, has as its mission to help users to learn a language while simultaneously using their learning exercises to translate the web. Language is learned through translation with, according to developers, Duolingo being as effective as any of the leading language learning software. For translating the web, machine translation is not good enough and relying only on professional translators, far too expensive. Duolingo, we are told, offers a third way, with translation as a by-product of its language learning. Translation which will be, if as promised, almost as cheap as if done by machines and almost as good as if by professionals. Launched in June 2012, Duolingo boasts already at the time of writing 300,000 active language learners ready for the task. This article independently assesses the extent to which Duolingo, at its current stage of development, meets those expectations.},
keywords = {A, Duolingo, language learning},
pubstate = {published},
tppubtype = {article}
}
Duolingo, a free online language learning site, has as its mission to help users to learn a language while simultaneously using their learning exercises to translate the web. Language is learned through translation with, according to developers, Duolingo being as effective as any of the leading language learning software. For translating the web, machine translation is not good enough and relying only on professional translators, far too expensive. Duolingo, we are told, offers a third way, with translation as a by-product of its language learning. Translation which will be, if as promised, almost as cheap as if done by machines and almost as good as if by professionals. Launched in June 2012, Duolingo boasts already at the time of writing 300,000 active language learners ready for the task. This article independently assesses the extent to which Duolingo, at its current stage of development, meets those expectations.
Vesselinov, Roumen; Grego, John
Duolingo Effectiveness Study Forschungsbericht
City University of New York and University of South Carolina 2012.
Abstract | Links | BibTeX | Schlagwörter: A, Duolingo, language learning
@techreport{Vesslinov2012,
title = {Duolingo Effectiveness Study},
author = {Roumen Vesselinov and John Grego},
url = {http://static.duolingo.com/s3/DuolingoReport_Final.pdf},
year = {2012},
date = {2012-12-01},
urldate = {2018-04-22},
institution = {City University of New York and University of South Carolina},
organization = {Duolingo},
abstract = {The research study of Duolingo effectiveness was independently conducted in September-November of 2012. The study lasted for approximately eight weeks. A random representative sample was selected from Duolingo users who studied Spanish. The participants were at least 18 years of age, native speakers of English, not from Hispanic origin and not advanced users of Spanish, and all of the participants resided in the United States.
The participants took one college placement Spanish language test in the beginning of the study and one test at the end of the study. The test results were measured in points (the higher the better). The improvement of language abilities was measured as the difference between the final and the initial language test results. The effectiveness of Duolingo was measured as language improvement per one hour of study.},
keywords = {A, Duolingo, language learning},
pubstate = {published},
tppubtype = {techreport}
}
The research study of Duolingo effectiveness was independently conducted in September-November of 2012. The study lasted for approximately eight weeks. A random representative sample was selected from Duolingo users who studied Spanish. The participants were at least 18 years of age, native speakers of English, not from Hispanic origin and not advanced users of Spanish, and all of the participants resided in the United States.
The participants took one college placement Spanish language test in the beginning of the study and one test at the end of the study. The test results were measured in points (the higher the better). The improvement of language abilities was measured as the difference between the final and the initial language test results. The effectiveness of Duolingo was measured as language improvement per one hour of study.
The participants took one college placement Spanish language test in the beginning of the study and one test at the end of the study. The test results were measured in points (the higher the better). The improvement of language abilities was measured as the difference between the final and the initial language test results. The effectiveness of Duolingo was measured as language improvement per one hour of study.