Ir directamente a la navegación principal Ir directamente a la búsqueda Ir directamente al contenido principal

Mistake Captioning: A Machine Learning Approach For Detecting Mistakes and Generating Instructive Feedback

Producción científica: Conference contribution › revisión exhaustiva

Resumen

Giving feedback to students is not just about marking their answers as correct or incorrect, but also finding mistakes in their thought process that led them to that incorrect answer. In this paper, we introduce a machine learning technique for mistake captioning, a task that attempts to identify mistakes and provide feedback meant to help learners correct these mistakes. We do this by training a sequence-to-sequence network to generate this feedback based on domain experts. To evaluate this system, we explore how it can be used on a Linguistics assignment studying Grimm's Law. We show that our approach generates feedback that outperforms a baseline on a set of automated NLP metrics. In addition, we perform a series of case studies in which we examine successful and unsuccessful system outputs.

Idioma originalEnglish
Título de la publicación alojadaInternational Conference Recent Advances in Natural Language Processing, RANLP 2021
Subtítulo de la publicación alojadaDeep Learning for Natural Language Processing Methods and Applications - Proceedings
EditoresGalia Angelova, Maria Kunilovskaya, Ruslan Mitkov, Ivelina Nikolova-Koleva
Páginas1455-1462
Número de páginas8
ISBN (versión digital)9789544520724
DOI
EstadoPublished - 2021
EventoInternational Conference on Recent Advances in Natural Language Processing: Deep Learning for Natural Language Processing Methods and Applications, RANLP 2021 - Virtual, Online
Duración: sept 1 2021 → sept 3 2021

Serie de la publicación

NombreInternational Conference Recent Advances in Natural Language Processing, RANLP
ISSN (versión impresa)1313-8502

Conference

ConferenceInternational Conference on Recent Advances in Natural Language Processing: Deep Learning for Natural Language Processing Methods and Applications, RANLP 2021
CiudadVirtual, Online
Período9/1/21 → 9/3/21

Nota bibliográfica

Publisher Copyright:
© 2021 Incoma Ltd. All rights reserved.

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Huella

Profundice en los temas de investigación de 'Mistake Captioning: A Machine Learning Approach For Detecting Mistakes and Generating Instructive Feedback'. En conjunto forman una huella única.

Citar esto