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 …

DeTiME: Diffusion-enhanced topic modeling using encoder-decoder based LLM

W Xu, W Hu, F Wu, S Sengamedu - arXiv preprint arXiv:2310.15296, 2023 - arxiv.org
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 …

[PDF][PDF] The state of the art in providing automated feedback to open-ended student work

P Larrondo, B Frank, J Ortiz - Proceedings of the Canadian …, 2021 - ojs.library.queensu.ca
THE STATE OF THE ART IN PROVIDING AUTOMATED FEEDBACK TO OPEN-ENDED
STUDENT WORK Page 1 Proceedings 2021 Canadian Engineering Education Association (CEEA-ACEG21) …

HR-MultiWOZ: A task oriented dialogue (TOD) dataset for HR LLM agent

W Xu, Z Huang, W Hu, X Fang, RK Cherukuri… - arXiv preprint arXiv …, 2024 - arxiv.org
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 …

S2vNTM: Semi-supervised vMF Neural Topic Modeling

W Xu, J Desai, S Sengamedu, X Jiang… - arXiv preprint arXiv …, 2023 - arxiv.org
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 …

HR-Agent: A Task-Oriented Dialogue (TOD) LLM Agent Tailored for HR Applications

W Xu, J Desai, F Wu, J Valvoda… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent LLM (Large Language Models) advancements benefit many fields such as
education and finance, but HR has hundreds of repetitive processes, such as access …

JADS: A Framework for Self-supervised Joint Aspect Discovery and Summarization

X Guo, J Desai, SH Sengamedu - arXiv preprint arXiv:2405.18642, 2024 - arxiv.org
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 …

[HTML][HTML] End-to-end question generation to assist formative assessment design for conceptual knowledge learning

J Zhao, W Xu, C Thille - 2021 - amazon.science
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 …

[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 …