ACTNext Podcast

How is ACT using NLP and GPT2 for Sphinx and other automatic content generation? In this episode of the Navigator podcast, we discuss Natural Language Processing with Yuchi Huang, a Senior Manager in the Artificial Intelligence and Machine Learning team at ACTNext. Yuchi takes us through some of the pitfalls and practices of using machine learning for text content analysis and generation.  A transcript is available at:  https://actnext.org/research-and-projects/podcast-ep-11-nlp-gpt2-sphinx/ The views and opinions expressed in this podcast are those of the authors only and do not necessarily reflect the official policy or position of ACT, Inc.

In this episode of the Navigator podcast, we discuss some of the artificial intelligence (AI) timeline, past, present and future, with Saad Khan , director of AI and machine learning for ACTNext. We'll learn how Saad's AI/ML team is using deep learning to create new tools for measurement and learning.

A transcript is available at:  https://actnext.org/research-and-projects/podcast-ep10-aiml-saad-khan/ ‎

In this podcast, we talk about learning with Dr. Vanessa Simmering. She's a Senior Research Scientist in Learning Solutions and studies learning and development.
In this interview, we talk about babies learning to crawl, walk, and run. We also discuss the Stroop Color and Word Test (try it here), crystallized versus fluid intelligence, and the dynamic systems theory of learning.

In this interview, Gunter Maris explains the theory behind The Wiring of Intelligence, a network model of learning.
Maris describes the actions of a “crazy electrician” who wires the connections in our brains. The network theory of intelligence developed by Maris (with colleagues Alexander Savi, Maarten Marsman, and Han van der Maas) is based on the idea of a house with interconnected electrical sockets in every room that represent synaptic knowledge.

In this episode of ACTNext Navigator podcast, we discuss some of the history of AIG at ACT and a couple new devices: AIG for assessing graphic literacy (AIGL) and passage organizing and extraction (POE). Guests: Rick Meisner, Ian MacMillan, Brad Bolender.

In this episode of ACTNext Navigator podcast, we’ll go under the hood of ACT's automated essay scoring engine, CRASE+.
Our guests are Erin Yao and Scott Wood. CRASE+ is a writing assessment tool that begins with human graders to develop a rubric. Data from human graders is used to train the automatic grading on a large scale.
We discuss CRASE+, automated scoring, the challenges of automated scoring using natural language processing, and how to address the biases in human graders.

In this episode, guest Jay Thomas, Senior Assessment Designer at ACT, discusses how eye-tracking can go beyond psychometrics to evaluate and validate assessment and testing.

With Langenfeld, Zhu, and Morris, he created a formula to measure Total Cognitive Effort (TCE) for test items.

In this episode, guests Yigal Rosen, Kristin Stoeffler, and Laurel Ozersky talk about the cross-cutting capabilities (CCCs) of creative and computational thinking. CCCs are part of ACT's Holistic Framework for college and career readiness.

Yigal and his group are leading some of the research and development in support of ACT’s transition to a learning company.

In addition to PISA, Yigal's Learning Solutions team is developing its own course work, called EDU2050.

We go in-depth on the CPSx game study that measures collaborative problem-solving. In this episode, Saad Kahn and Dave Edwards discuss the game, "Crisis in Space," they use to gather data from players. The data comes from natural language processing, eye-tracking, and other records.

In this episode of ACTNext Navigator, we discuss the inter-ACT collaboration between ACTNext and the ACT Center for Equity in Learning (CEL). The next Navigator podcast, Episode 3, will examine the game design and research that will come out of the study.