Agent Smith: Teaching Question Answering to Jill Watson

Goel, Ashok K.; Sikka, Harshvardhan; Eric, Gregori,

doi:10.48550/arxiv.2112.13677

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As another example, AI-ALOE is evolving an AI tool called Jill Watson for enhancing teacher presence by automatically answering questions posed by learners in online discussion forums any time, any place [13]. Jill Watson combines digital libraries for storing answers to previously asked questions, natural language processing for classifying new questions, and machine learning techniques for retrieving answers and generating a novel answer for the new question.…”

Section: The Goal Of Engagement At Scalementioning

confidence: 99%

Developing a Next-Generation Model for Massive Digital Learning

Dede,

Lidwell

2023

Education Sciences

View full text Add to dashboard Cite

A decade ago, massively open online courses (MOOCs) were heralded as the solution to universal, global access to higher education. While they failed to reach this vision, primarily because of teaching-by-telling and learning-by-listening (a PDF of the residential classroom), MOOCs provided the foundational models and infrastructure for emergency remote learning in the pandemic. Reports of remote learning’s death post-pandemic are greatly exaggerated, since the world is now irreversibly hybrid—and will stay that way because many people and organizations value the new opportunities this presents. From now on, when students leave the shelter of classrooms to interact with the world beyond schooling, they must have skills for adept performance both face-to-face and across distance. Colleges, universities, and regions that force all teaching and learning to be face-to-face are dooming their graduates to reduced agency in every other aspect of life. As discussed in recent reports from Harvard, MIT, and Stanford, innovative approaches to digital learning were developed during the pandemic that are now improving campus-based learning. Insights from these approaches offer the opportunity for student engagement at scale, taking advantage of strengths of online instruction such as collapsing time, bridging space, personalizing via rich datastreams, using AI-based instructional assistants and learning partners, delivering content and experience across universities, and sustaining online learning communities after formal instruction ends. Combined, these advances can enable next-generation massive digital hybrid learning, a means to achieve the aspirational vision of universal global access to higher education. A coalition of higher education institutions could begin to realize this vision, an essential step in enabling all learners to survive and thrive in our increasingly turbulent, disruptive global economy and civilization.

show abstract

Section: The Goal Of Engagement At Scalementioning

confidence: 99%

Developing a Next-Generation Model for Massive Digital Learning

Dede,

Lidwell

2023

Education Sciences

View full text Add to dashboard Cite

show abstract

Enhancing educational Q&A systems using a Chaotic Fuzzy Logic-Augmented large language model

Chen,

Shi,

Chen

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

IntroductionOnline question-and-answer (Q&A) platforms are frequently replete with extensive human resource support. This study proposes a novel methodology of a customized large language model (LLM) called Chaotic LLM-based Educational Q&A System (CHAQS) to navigate the complexities associated with intelligent Q&A systems for the educational sector.MethodsIt uses an expansive dataset comprising over 383,000 educational data pairs, an intricate fine-tuning process encompassing p-tuning v2, low-rank adaptation (LRA), and strategies for parameter freezing at an open-source large language model ChatGLM as a baseline model. In addition, Fuzzy Logic is implemented to regulate parameters and the system's adaptability with the Lee Oscillator to refine the model's response variability and precision.ResultsExperiment results showed a 5.12% improvement in precision score, an 11% increase in recall metric, and an 8% improvement in the F1 score as compared to other models.DiscussionThese results suggest that the CHAQS methodology significantly enhances the performance of educational Q&A systems, demonstrating the effectiveness of combining advanced tuning techniques and fuzzy logic for improved model precision and adaptability.

show abstract

Agent Smith: Teaching Question Answering to Jill Watson

Cited by 2 publications

References 0 publications

Developing a Next-Generation Model for Massive Digital Learning

Developing a Next-Generation Model for Massive Digital Learning

Enhancing educational Q&A systems using a Chaotic Fuzzy Logic-Augmented large language model

Contact Info

Product

Resources

About