NLP, GPT2 and Sphinx

enMay 20, 2020

ACTNext Podcast

What was the main topic of the podcast episode?

Summarise the key points discussed in the episode?

Were there any notable quotes or insights from the speakers?

Which popular books were mentioned in this episode?

Were there any points particularly controversial or thought-provoking discussed in the episode?

Were any current events or trending topics addressed in the episode?

What was the main topic of the podcast episode?

Summarise the key points discussed in the episode?

Were there any notable quotes or insights from the speakers?

Which popular books were mentioned in this episode?

Were there any points particularly controversial or thought-provoking discussed in the episode?

Were any current events or trending topics addressed in the episode?

About this Episode

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,Â 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.Â A transcript is available at: Â https://actnext.org/research-and-projects/podcast-ep-11-nlp-gpt2-sphinx/ TheÂ viewsÂ and opinionsÂ expressedÂ in this podcast are those of the authors only and do not necessarily reflect the official policy or position of ACT, Inc.

Recent Episodes from ACTNext Podcast

NLP, GPT2 and Sphinx

enMay 20, 2020

Talking AI/ML and Deep Learning

In this episode of the Navigator podcast, we discuss some of the artificial intelligence (AI) timeline, past, present and future, with Saad KhanÂ , 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: Â https://actnext.org/research-and-projects/podcast-ep10-aiml-saad-khan/Â â

enApril 03, 2020

What is learning?

In this podcast, we talk about learning withÂ 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.

enMarch 06, 2020

The Wiring of Intelligence

In this interview, Gunter Maris explains the theory behind The Wiring of Intelligence, a network model of learning.
Maris describes the actions of a âcrazy electricianâ who wires the connections in our brains. The network theory of intelligence developed by Maris (with colleagues Alexander Savi,Â 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.

enJanuary 27, 2020

Creating Test Items with Automated Item Generation

In this episode ofÂ 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.

enJanuary 02, 2020

Explaining the Grade: Auto Essay Scoring and CRASE+

In this episode of ACTNext Navigator podcast, weâll 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.

enNovember 21, 2019

Validating Cognitive Processes with Eye-Tracking

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.

enNovember 19, 2019

Cross-Cutting Capabilities of Creative and Computational Thinking

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 FrameworkÂ for college and career readiness.

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

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

enOctober 04, 2019

CPSx Game Study

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.

enAugust 20, 2019

Collaboration with CEL at ACT

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.

enJuly 29, 2019

Ask this episode Anything

What was the main topic of the podcast episode?

Summarise the key points discussed in the episode?

Were there any notable quotes or insights from the speakers?

Which popular books were mentioned in this episode?

Were there any points particularly controversial or thought-provoking discussed in the episode?

Were any current events or trending topics addressed in the episode?