We are looking to recruit three postdoctoral researchers in the MBZUAI (Mohamed bin Zayed University of Artificial Intelligence) Department of Natural Language Processing to work with myself and Prof. Ted Briscoe. The three projects will broadly focus on:
Qualifications
Applicants should have:
Application Instructions
Apply via https://apply.interfolio.com/124150
The positions are available for 2 years initially starting 1st September 2023 with a possibility of subsequent renewal. The salary is tax-free and competitive (approx. USD 75-100K) depending on experience. The benefits include medical insurance, support with relocation and visa application, 30 calendar days vacation leave per year, and generous support for conference attendance.
Informal enquiries concerning the projects can be directed to the Faculty Affairs team facultyaffairs@mbzuai.ac.ae.
]]>The piece of information that is mostly missing though and that is of critical importance is how pedagogically useful and applicable these models really are in educational contexts. We have investigated these questions in our recent paper titled “How Useful are Educational Questions Generated by Large Language Models?”. This work is a collaboration between Sabina Elkins (McGill University, MILA, & Korbit), myself, Jackie Chi Kit Cheung (McGill University & MILA), and Iulian Serban (Korbit).
In this study, we used controllable generation and few-shot learning to generate diverse educational questions at different levels of Bloom’s taxonomy and at varying difficulty levels across two subject domains. We then asked a set of teachers to assess these questions to determine if – from their perspective – these questions are high quality and viable for use in the classroom.
Overwhelmingly, the answer is yes! We can generate relevant, grammatically correct, and answerable questions, the quality and usefulness of which speaks volumes about how they can benefit teachers and students alike.
The paper will appear in the proceedings of the 24th International Conference on Artificial Intelligence in Education (AIED 2023) later this year, but you can already access its preprint version here. Moreover, if you’d like to learn more about the study and the annotators and see the examples of the generated questions, take a look at our github page for this study.
]]>I will be looking to hire PhD students and postdocs to work with me on the topics in NLP and applications of AI to education. If you are interested in working with me as a PhD student or a postdoc, please get in touch.
As a prospective PhD student, you may also find the University’s webpages useful.
]]>Title: Automated Generation of Pedagogical Interventions in Dialogue-based Intelligent Tutoring Systems
Abstract: Despite artificial intelligence (AI) having transformed major aspects of our society, only a fraction of its potential has been explored, let alone deployed, for education. AI-powered learning can provide millions of learners with personalised, active and practical learning experiences, which are key to successful learning. This is especially relevant in the context of online learning platforms. In this talk, I will present the Korbit Intelligent Tutoring System (ITS), which provides a dialogue-based learning experience online. Specifically, Korbit relies on the Socratic tutoring method: presentation of learning material is followed by a series of questions and pedagogical interventions from the AI-tutor aimed at promoting deliberation, guiding the learner and setting the line of reasoning. I will describe the AI approaches that we use to provide learners with highly personalised and active learning experiences via dialogue. Finally, I will present and discuss the results of a comparative head-to-head study on learning outcomes for Korbit and a popular MOOC platform that follows a traditional model delivering content using lecture videos and multiple-choice quizzes. Our experiments demonstrate a significant increase in learning outcomes, with students on the Korbit platform showing higher course completion rates and achieving learning gains 2 to 2.5 times higher than students on an online platform who do not receive dialogue-based feedback. These results highlight the tremendous impact that can be achieved with a dialogue-based AI-powered system, making high-quality learning experiences available to millions of learners around the world.
]]>The book is finally out. It is called “Getting Started with Natural Language Processing” and it is published with Manning. It contains lots of accessible explanations and hands-on examples through which you will learn how to apply NLP to sentiment analysis, user profiling, topic modelling, information search, named entity recognition, and other tasks. As you go, each new project builds on what you’ve previously learned, introducing new concepts and skills.
The book is available via Manning and Amazon.
Book’s GitHub repo.
]]>If you represent a society and would like to be an IAALDE member, please check the membership details here.
]]>