vONTSS: vMF based semi-supervised neural topic modeling with optimal transport
W Xu, X Jiang, SH Sengamedu, F Iannacci… - arXiv preprint arXiv …, 2023 - arxiv.org
Recently, Neural Topic Models (NTM), inspired by variational autoencoders, have attracted
a lot of research interest; however, these methods have limited applications in the real world …
a lot of research interest; however, these methods have limited applications in the real world …
DeTiME: Diffusion-enhanced topic modeling using encoder-decoder based LLM
In the burgeoning field of natural language processing, Neural Topic Models (NTMs) and
Large Language Models (LLMs) have emerged as areas of significant research interest …
Large Language Models (LLMs) have emerged as areas of significant research interest …
[PDF][PDF] The state of the art in providing automated feedback to open-ended student work
THE STATE OF THE ART IN PROVIDING AUTOMATED FEEDBACK TO OPEN-ENDED
STUDENT WORK Page 1 Proceedings 2021 Canadian Engineering Education Association (CEEA-ACEG21) …
STUDENT WORK Page 1 Proceedings 2021 Canadian Engineering Education Association (CEEA-ACEG21) …
HR-MultiWOZ: A task oriented dialogue (TOD) dataset for HR LLM agent
Recent advancements in Large Language Models (LLMs) have been reshaping Natural
Language Processing (NLP) task in several domains. Their use in the field of Human …
Language Processing (NLP) task in several domains. Their use in the field of Human …
S2vNTM: Semi-supervised vMF Neural Topic Modeling
Language model based methods are powerful techniques for text classification. However,
the models have several shortcomings.(1) It is difficult to integrate human knowledge such …
the models have several shortcomings.(1) It is difficult to integrate human knowledge such …
HR-Agent: A Task-Oriented Dialogue (TOD) LLM Agent Tailored for HR Applications
Recent LLM (Large Language Models) advancements benefit many fields such as
education and finance, but HR has hundreds of repetitive processes, such as access …
education and finance, but HR has hundreds of repetitive processes, such as access …
JADS: A Framework for Self-supervised Joint Aspect Discovery and Summarization
To generate summaries that include multiple aspects or topics for text documents, most
approaches use clustering or topic modeling to group relevant sentences and then generate …
approaches use clustering or topic modeling to group relevant sentences and then generate …
[HTML][HTML] End-to-end question generation to assist formative assessment design for conceptual knowledge learning
Formative assessment can be used by learning designers to evaluate a learners'
comprehension, learning needs, and learning progress during a lesson, unit, or course. The …
comprehension, learning needs, and learning progress during a lesson, unit, or course. The …
[HTML][HTML] Building an infrastructure for A/B experiments at scale: The challenges, opportunities, and lessons for the learning analytics community
S Sankaranarayanan, C Harrison, S Kumari, K Larson… - 2023 - amazon.science
A/B testing at scale provides opportunities for learning analytics researchers to learn from
large sample sizes. Deploying and running live intervention experiments with such large …
large sample sizes. Deploying and running live intervention experiments with such large …