Corpus ID: 195658099

Creating A Neural Pedagogical Agent by Jointly Learning to Review and Assess

  title={Creating A Neural Pedagogical Agent by Jointly Learning to Review and Assess},
  author={Youngnam Lee and Youngduck Choi and Junghyun Cho and Alexander R. Fabbri and Hyunbin Loh and Chanyou Hwang and Yongku Lee and Sang-Wook Kim and Dragomir R. Radev},
Machine learning plays an increasing role in intelligent tutoring systems as both the amount of data available and specialization among students grow. Nowadays, these systems are frequently deployed on mobile applications. Users on such mobile education platforms are dynamic, frequently being added, accessing the application with varying levels of focus, and changing while using the service. The education material itself, on the other hand, is often static and is an exhaustible resource whose… Expand
Assessment Modeling: Fundamental Pre-training Tasks for Interactive Educational Systems
This work proposes assessment modeling as a guiding principle for selecting proper pre- training tasks for the label-scarce educational problems, and is the first work investigating appropriate pre-training method of predicting educational features from student-system interactions. Expand
Individualized AI Tutor Based on Developmental Learning Networks
An individualized AI tutor is proposed as an integrated system of three developmental learning networks (DLNs) by extending a deep adaptive resonance theory (Deep ART) network, a neural network capable of incremental learning. Expand
New Trends in Pedagogical Agents in Education
A pedagogical agent is an anthropomorphic virtual character used in an online learning environment for educational purposes. Pedagogical Agents fulfill a variety of educational purposes, for whichExpand
Recommendation for Effective Standardized Exam Preparation
  • Hyunbin Loh, Dongmin Shin, +7 authors Youngduck Choi
  • Computer Science
  • LAK
  • 2021
A recommender system that optimizes the learning trajectory of a student preparing for a standardized exam by recommending the learning content which directly maximizes the expected score after the consumption of the content is proposed. Expand
Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing
This is the first work to suggest an encoder-decoder model for knowledge tracing that applies deep self-attentive layers to exercises and responses separately and achieves state-of-the-art performance in knowledge tracing with an improvement in area under receiver operating characteristic curve (AUC). Expand
Last Query Transformer RNN for knowledge tracing
An efficient model to predict a student's answer correctness given his past learning activities, that only uses the last input as query in transformer encoder, which makes QK matrix multiplication in transformer Encoder to have O(L) time complexity, instead of O( L^2). Expand
EdNet: A Large-Scale Hierarchical Dataset in Education
EdNet is introduced, a large-scale hierarchical dataset of diverse student activities collected by Santa, a multi-platform self-study solution equipped with an artificial intelligence tutoring system, making it the largest public IES dataset released to date. Expand
MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education
MathBERT, a BERT pre-trained on large mathematical corpus including pre-k to graduate level mathematical content to tackle math-specific tasks is proposed and is the first pre- trained model for general purpose mathematics education tasks. Expand
SAINT+: Integrating Temporal Features for EdNet Correctness Prediction
SAINT+, a successor of SAINT which is a Transformer based knowledge tracing model that separately processes exercise information and student response information, achieves state-of-the-art performance in knowledge tracing with an improvement of 1.25% in area under receiver operating characteristic curve compared to SAINT. Expand
Deep Attentive Study Session Dropout Prediction in Mobile Learning Environment
A novel Transformer based model for predicting study session dropout, DAS: Deep Attentive Study Session Dropout Prediction in Mobile Learning Environment is proposed which achieves the best performance with a significant improvement in area under the receiver operating characteristic curve compared to baseline models. Expand


Learn and Evolve the Domain Model in Intelligent Tutoring Systems - Approach Based on Interaction Traces
A novel approach to fill a gap by the semi-automatic reorganization of the domain knowledge in a way that can potentially maximize students’ learning by updating knowledge domain and learner profiles from the interaction traces. Expand
AI in Education needs interpretable machine learning: Lessons from Open Learner Modelling
It is argued that this work can provide a valuable starting point for a framework of interpretable AI, and is of relevance to the application of both knowledge-based and machine learning systems in other high-stakes contexts, beyond education. Expand
Learning analytics: Collaborative filtering or regression with experts?
This work proposes a new model for test responses, and proposes a collaborative filtering algorithm with enhanced human-interpretability based on the new model, and evaluates the prediction performance of these approaches using a large education data set. Expand
Recommender system for predicting student performance
A novel approach which uses recommender system techniques for educational data mining, especially for predicting student performance, and is compared with traditional regression methods such as logistic/linear regression by using educational data for intelligent tutoring systems. Expand
Artificial Intelligence as an Effective Classroom Assistant
The field of artificial intelligence in education (AIED) uses techniques from AI and cognitive science to better understand the nature of learning and teaching and to build systems to help learnersExpand
Enhancing learning outcomes through self-regulated learning support with an Open Learner Model
Two classroom experiments support the notion that an OLM can enhance students’ domain-level learning outcomes through scaffolding of SRL processes, and are among the first in-vivo classroom experiments to do so. Expand
Requirements for Mobile Learning Applications in Higher Education
In the first part of the paper a requirements analysis for an adjusted mobile version of the learn management system (LMS) Stud.IP is presented and the implementation of an Android-based and web-based app for the LMS Stud. Expand
Deep Learning Based Recommender System
A taxonomy of deep learning-based recommendation models is provided and a comprehensive summary of the state of the art is provided, along with new perspectives pertaining to this new and exciting development of the field. Expand
Attention is All you Need
A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data. Expand
Effective Approaches to Attention-based Neural Machine Translation
A global approach which always attends to all source words and a local one that only looks at a subset of source words at a time are examined, demonstrating the effectiveness of both approaches on the WMT translation tasks between English and German in both directions. Expand