إن تقديم ملاحظات للطلاب ليس فقط في وضع علامة على إجاباتهم على النحو الصحيح أو غير صحيح، ولكن أيضا العثور على أخطاء في عملية التفكير التي دفعتهم إلى الإجابة غير الصحيحة.في هذه الورقة، نقدم تقنية لتعلم الآلات بسبب التسمية التوضيحية، وهي مهمة تحاول تحديد الأخطاء وتوفير التعليقات مخصصة لمساعدة المتعلمين على تصحيح هذه الأخطاء.نقوم بذلك عن طريق تدريب شبكة تسلسل إلى تسلسل لتوليد هذه التعليقات بناء على خبراء المجال.لتقييم هذا النظام، نستكشف كيف يمكن استخدامه في مهمة اللغويات التي تدرس قانون جريم.نظهر أن نهجنا يولد ردود الفعل التي تتفوق على خط أساس على مجموعة من مقاييس NLP الآلية.بالإضافة إلى ذلك، نقوم بإجراء سلسلة من دراسات الحالة التي ندرس فيها مخرجات النظام الناجحة وغير الناجحة.
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.
References used
https://aclanthology.org/
Post processing is the most conventional approach for correcting errors that are caused by Optical Character Recognition(OCR) systems. Two steps are usually taken to correct OCR errors: detection and corrections. For the first task, supervised machin
We investigate the question of how adaptive feedback from a virtual agent impacts the linguistic input of the user in a shared world game environment. To do so, we carry out an exploratory pilot study to observe how individualized linguistic feedback
The reported work is a description of our participation in the Classification of COVID19 tweets containing symptoms'' shared task, organized by the Social Media Mining for Health Applications (SMM4H)'' workshop. The literature describes two machine l
In this paper we describe the systems used by the RoMa team in the shared task on Detecting and Rating Humor and Offense (HaHackathon) at SemEval 2021. Our systems rely on data representations learned through fine-tuned neural language models. Partic
With counterfactual bandit learning, models can be trained based on positive and negative feedback received for historical predictions, with no labeled data needed. Such feedback is often available in real-world dialog systems, however, the modulariz