603 citations · 1.2k across the 21 of their papers we have counts for
30 papers
PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution
Pierre-Luc St-Charles, Alessandro Palmas, Damiano Fornasiere +5
Reasoning models can remain capable of solving a task while still defaulting to cheaper but misleading shortcuts. This creates a central oversight problem: when a model gives an an…
Safety from Honesty in a Disinterested AI Predictor
Yoshua Bengio, Oliver Richardson, Tomáš Gavenčiak +13
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified…
How Teachers Can Use Large Language Models and Bloom's Taxonomy to Create Educational Quizzes
Sabina Elkins, Ekaterina Kochmar, Jackie C. K. Cheung +1
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 re…
How Useful are Educational Questions Generated by Large Language Models?
Sabina Elkins, Ekaterina Kochmar, Jackie C. K. Cheung +1
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 ques…
Raising Student Completion Rates with Adaptive Curriculum and Contextual Bandits
Robert Belfer, Ekaterina Kochmar, Iulian Vlad Serban
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 studen…
Few-shot Question Generation for Personalized Feedback in Intelligent Tutoring Systems
Devang Kulshreshtha, Muhammad Shayan, Robert Belfer +3
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 que…
Question Personalization in an Intelligent Tutoring System
Sabina Elkins, Robert Belfer, Ekaterina Kochmar +2
This paper investigates personalization in the field of intelligent tutoring systems (ITS). We hypothesize that personalization in the way questions are asked improves student lear…
A New Era: Intelligent Tutoring Systems Will Transform Online Learning for Millions
Francois St-Hilaire, Dung Do Vu, Antoine Frau +28
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…
Comparative Study of Learning Outcomes for Online Learning Platforms
Francois St-Hilaire, Nathan Burns, Robert Belfer +16
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…
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval
Devang Kulshreshtha, Robert Belfer, Iulian Vlad Serban +1
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 synth…
Deep Discourse Analysis for Generating Personalized Feedback in Intelligent Tutor Systems
Matt Grenander, Robert Belfer, Ekaterina Kochmar +3
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…
Automated Personalized Feedback Improves Learning Gains in an Intelligent Tutoring System
Ekaterina Kochmar, Dung Do Vu, Robert Belfer +3
We investigate how automated, data-driven, personalized feedback in a large-scale intelligent tutoring system (ITS) improves student learning outcomes. We propose a machine learnin…
A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM
Iulian Vlad Serban, Varun Gupta, Ekaterina Kochmar +6
We present Korbit, a large-scale, open-domain, mixed-interface, dialogue-based intelligent tutoring system (ITS). Korbit uses machine learning, natural language processing and rein…
The Second Conversational Intelligence Challenge (ConvAI2)
Emily Dinan, Varvara Logacheva, Valentin Malykh +14
We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots. Some key takeaways from the competition ar…
The RLLChatbot: a solution to the ConvAI challenge
Nicolas Gontier, Koustuv Sinha, Peter Henderson +4
Current conversational systems can follow simple commands and answer basic questions, but they have difficulty maintaining coherent and open-ended conversations about specific topi…
The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach
Iulian Vlad Serban, Chinnadhurai Sankar, Michael Pieper +2
Deep reinforcement learning has recently shown many impressive successes. However, one major obstacle towards applying such methods to real-world problems is their lack of data-eff…
A Deep Reinforcement Learning Chatbot (Short Version)
Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain +15
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capa…
A Deep Reinforcement Learning Chatbot
Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain +15
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capa…
Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses
Ryan Lowe, Michael Noseworthy, Iulian V. Serban +3
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and co…
Piecewise Latent Variables for Neural Variational Text Processing
Iulian V. Serban, Alexander G. Ororbia, Joelle Pineau +1
Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variables, such as variational autoencoders. The…
Generative Deep Neural Networks for Dialogue: A Short Review
Iulian Vlad Serban, Ryan Lowe, Laurent Charlin +1
Researchers have recently started investigating deep neural networks for dialogue applications. In particular, generative sequence-to-sequence (Seq2Seq) models have shown promising…
Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
Iulian Vlad Serban, Tim Klinger, Gerald Tesauro +4
We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic…
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe +4
Sequential data often possesses a hierarchical structure with complex dependencies between subsequences, such as found between the utterances in a dialogue. In an effort to model t…
Theano: A Python framework for fast computation of mathematical expressions
The Theano Development Team, Rami Al-Rfou, Guillaume Alain +110
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has bee…