Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Serban, Iulian"'
Question generation (QG) is a natural language processing task with an abundance of potential benefits and use cases in the educational domain. In order for this potential to be realized, QG systems must be designed and validated with pedagogical nee
Externí odkaz:
http://arxiv.org/abs/2401.05914
Controllable text generation (CTG) by large language models has a huge potential to transform education for teachers and students alike. Specifically, high quality and diverse question generation can dramatically reduce the load on teachers and impro
Externí odkaz:
http://arxiv.org/abs/2304.06638
We present an adaptive learning Intelligent Tutoring System, which uses model-based reinforcement learning in the form of contextual bandits to assign learning activities to students. The model is trained on the trajectories of thousands of students
Externí odkaz:
http://arxiv.org/abs/2207.14003
Autor:
Kulshreshtha, Devang, Shayan, Muhammad, Belfer, Robert, Reddy, Siva, Serban, Iulian Vlad, Kochmar, Ekaterina
Existing work on generating hints in Intelligent Tutoring Systems (ITS) focuses mostly on manual and non-personalized feedback. In this work, we explore automatically generated questions as personalized feedback in an ITS. Our personalized feedback c
Externí odkaz:
http://arxiv.org/abs/2206.04187
This paper investigates personalization in the field of intelligent tutoring systems (ITS). We hypothesize that personalization in the way questions are asked improves student learning outcomes. Previous work on dialogue-based ITS personalization has
Externí odkaz:
http://arxiv.org/abs/2206.14145
Autor:
St-Hilaire, Francois, Vu, Dung Do, Frau, Antoine, Burns, Nathan, Faraji, Farid, Potochny, Joseph, Robert, Stephane, Roussel, Arnaud, Zheng, Selene, Glazier, Taylor, Romano, Junfel Vincent, Belfer, Robert, Shayan, Muhammad, Smofsky, Ariella, Delarosbil, Tommy, Ahn, Seulmin, Eden-Walker, Simon, Sony, Kritika, Ching, Ansona Onyi, Elkins, Sabina, Stepanyan, Anush, Matajova, Adela, Chen, Victor, Sahraei, Hossein, Larson, Robert, Markova, Nadia, Barkett, Andrew, Charlin, Laurent, Bengio, Yoshua, Serban, Iulian Vlad, Kochmar, Ekaterina
Despite artificial intelligence (AI) having transformed major aspects of our society, less than a fraction of its potential has been explored, let alone deployed, for education. AI-powered learning can provide millions of learners with a highly perso
Externí odkaz:
http://arxiv.org/abs/2203.03724
Autor:
Serban, Iulian Vlad
Cette thèse présente une série de mesures prises pour étudier l’apprentissage de représentations (par exemple, l’apprentissage profond) afin de mettre en place des systèmes de dialogue et des agents de conversation virtuels. La thèse est d
Externí odkaz:
http://hdl.handle.net/1866/23440
In this work, we introduce back-training, an alternative to self-training for unsupervised domain adaptation (UDA) from source to target domain. While self-training generates synthetic training data where natural inputs are aligned with noisy outputs
Externí odkaz:
http://arxiv.org/abs/2104.08801
Autor:
St-Hilaire, Francois, Burns, Nathan, Belfer, Robert, Shayan, Muhammad, Smofsky, Ariella, Vu, Dung Do, Frau, Antoine, Potochny, Joseph, Faraji, Farid, Pavero, Vincent, Ko, Neroli, Ching, Ansona Onyi, Elkins, Sabina, Stepanyan, Anush, Matajova, Adela, Charlin, Laurent, Bengio, Yoshua, Serban, Iulian Vlad, Kochmar, Ekaterina
Personalization and active learning are key aspects to successful learning. These aspects are important to address in intelligent educational applications, as they help systems to adapt and close the gap between students with varying abilities, which
Externí odkaz:
http://arxiv.org/abs/2104.07763
Autor:
Grenander, Matt, Belfer, Robert, Kochmar, Ekaterina, Serban, Iulian V., St-Hilaire, François, Cheung, Jackie C. K.
We explore creating automated, personalized feedback in an intelligent tutoring system (ITS). Our goal is to pinpoint correct and incorrect concepts in student answers in order to achieve better student learning gains. Although automatic methods for
Externí odkaz:
http://arxiv.org/abs/2103.07785