[HTML][HTML] ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope

PP Ray - Internet of Things and Cyber-Physical Systems, 2023 - Elsevier
In recent years, artificial intelligence (AI) and machine learning have been transforming the
landscape of scientific research. Out of which, the chatbot technology has experienced …

ChatGPT-like large-scale foundation models for prognostics and health management: A survey and roadmaps

YF Li, H Wang, M Sun - Reliability Engineering & System Safety, 2024 - Elsevier
PHM technology is vital in industrial production and maintenance, identifying and predicting
potential equipment failures and damages. This enables proactive maintenance measures …

Merlot: Multimodal neural script knowledge models

R Zellers, X Lu, J Hessel, Y Yu… - Advances in neural …, 2021 - proceedings.neurips.cc
As humans, we understand events in the visual world contextually, performing multimodal
reasoning across time to make inferences about the past, present, and future. We introduce …

Perturbed masking: Parameter-free probing for analyzing and interpreting BERT

Z Wu, Y Chen, B Kao, Q Liu - arxiv preprint arxiv:2004.14786, 2020 - arxiv.org
By introducing a small set of additional parameters, a probe learns to solve specific linguistic
tasks (eg, dependency parsing) in a supervised manner using feature representations (eg …

Predicting the next sentence (not word) in large language models: What model-brain alignment tells us about discourse comprehension

S Yu, C Gu, K Huang, P Li - Science advances, 2024 - science.org
Current large language models (LLMs) rely on word prediction as their backbone pretraining
task. Although word prediction is an important mechanism underlying language processing …

A survey of methods for addressing class imbalance in deep-learning based natural language processing

S Henning, W Beluch, A Fraser, A Friedrich - arxiv preprint arxiv …, 2022 - arxiv.org
Many natural language processing (NLP) tasks are naturally imbalanced, as some target
categories occur much more frequently than others in the real world. In such scenarios …

A novel automated essay scoring approach for reliable higher educational assessments

M Beseiso, OA Alzubi, H Rashaideh - Journal of Computing in Higher …, 2021 - Springer
E-learning is gradually gaining prominence in higher education, with universities enlarging
provision and more students getting enrolled. The effectiveness of automated essay scoring …

Discoprompt: Path prediction prompt tuning for implicit discourse relation recognition

C Chan, X Liu, J Cheng, Z Li, Y Song, GY Wong… - arxiv preprint arxiv …, 2023 - arxiv.org
Implicit Discourse Relation Recognition (IDRR) is a sophisticated and challenging task to
recognize the discourse relations between the arguments with the absence of discourse …

Unleashing the transformers: NLP models detect AI writing in education

J Campino - Journal of Computers in Education, 2024 - Springer
Artificial Intelligence (AI) has witnessed widespread application across diverse domains,
with education being a prominent focus for enhancing learning outcomes and tailoring …

ByGPT5: End-to-end style-conditioned poetry generation with token-free language models

J Belouadi, S Eger - arxiv preprint arxiv:2212.10474, 2022 - arxiv.org
State-of-the-art poetry generation systems are often complex. They either consist of task-
specific model pipelines, incorporate prior knowledge in the form of manually created …