Zobrazeno 1 - 10
of 224
pro vyhledávání: '"HEFFERNAN, Neil"'
Autor:
Denny, Paul, Gulwani, Sumit, Heffernan, Neil T., Käser, Tanja, Moore, Steven, Rafferty, Anna N., Singla, Adish
This survey article has grown out of the GAIED (pronounced "guide") workshop organized by the authors at the NeurIPS 2023 conference. We organized the GAIED workshop as part of a community-building effort to bring together researchers, educators, and
Externí odkaz:
http://arxiv.org/abs/2402.01580
Randomized A/B tests within online learning platforms represent an exciting direction in learning sciences. With minimal assumptions, they allow causal effect estimation without confounding bias and exact statistical inference even in small samples.
Externí odkaz:
http://arxiv.org/abs/2306.06273
Automated scoring of student responses to open-ended questions, including short-answer questions, has great potential to scale to a large number of responses. Recent approaches for automated scoring rely on supervised learning, i.e., training classif
Externí odkaz:
http://arxiv.org/abs/2306.00791
Automatic short answer grading is an important research direction in the exploration of how to use artificial intelligence (AI)-based tools to improve education. Current state-of-the-art approaches use neural language models to create vectorized repr
Externí odkaz:
http://arxiv.org/abs/2205.15219
This survey article has grown out of the RL4ED workshop organized by the authors at the Educational Data Mining (EDM) 2021 conference. We organized this workshop as part of a community-building effort to bring together researchers and practitioners i
Externí odkaz:
http://arxiv.org/abs/2107.08828
Autor:
Shen, Jia Tracy, Yamashita, Michiharu, Prihar, Ethan, Heffernan, Neil, Wu, Xintao, Graff, Ben, Lee, Dongwon
Since the introduction of the original BERT (i.e., BASE BERT), researchers have developed various customized BERT models with improved performance for specific domains and tasks by exploiting the benefits of transfer learning. Due to the nature of ma
Externí odkaz:
http://arxiv.org/abs/2106.07340
Autor:
Shen, Jia Tracy, Yamashita, Michiharu, Prihar, Ethan, Heffernan, Neil, Wu, Xintao, McGrew, Sean, Lee, Dongwon
Educational content labeled with proper knowledge components (KCs) are particularly useful to teachers or content organizers. However, manually labeling educational content is labor intensive and error-prone. To address this challenge, prior research
Externí odkaz:
http://arxiv.org/abs/2105.11343
Autor:
Gagnon-Bartsch, Johann A., Sales, Adam C., Wu, Edward, Botelho, Anthony F., Erickson, John A., Miratrix, Luke W., Heffernan, Neil T.
Randomized controlled trials (RCTs) are increasingly prevalent in education research, and are often regarded as a gold standard of causal inference. Two main virtues of randomized experiments are that they (1) do not suffer from confounding, thereby
Externí odkaz:
http://arxiv.org/abs/2105.03529
Autor:
Gagnon-Bartsch Johann A., Sales Adam C., Wu Edward, Botelho Anthony F., Erickson John A., Miratrix Luke W., Heffernan Neil T.
Publikováno v:
Journal of Causal Inference, Vol 11, Iss 1, Pp 286-327 (2023)
Randomized controlled trials (RCTs) admit unconfounded design-based inference – randomization largely justifies the assumptions underlying statistical effect estimates – but often have limited sample sizes. However, researchers may have access to
Externí odkaz:
https://doaj.org/article/72c13472c43e45d68eed97512853c58a
Personalized recommendation based on multi-arm bandit (MAB) algorithms has shown to lead to high utility and efficiency as it can dynamically adapt the recommendation strategy based on feedback. However, unfairness could incur in personalized recomme
Externí odkaz:
http://arxiv.org/abs/2010.12102