Simple and principled uncertainty estimation with deterministic deep learning via distance awareness
Bayesian neural networks (BNN) and deep ensembles are principled approaches to
estimate the predictive uncertainty of a deep learning model. However their practicality in …
estimate the predictive uncertainty of a deep learning model. However their practicality in …
A simple approach to improve single-model deep uncertainty via distance-awareness
Accurate uncertainty quantification is a major challenge in deep learning, as neural
networks can make overconfident errors and assign high confidence predictions to out-of …
networks can make overconfident errors and assign high confidence predictions to out-of …
A survey of intent classification and slot-filling datasets for task-oriented dialog
Interest in dialog systems has grown substantially in the past decade. By extension, so too
has interest in developing and improving intent classification and slot-filling models, which …
has interest in developing and improving intent classification and slot-filling models, which …
Prototyping a Chatbot for site managers using building information modeling (BIM) and natural language understanding (NLU) techniques
WY Lin - Sensors, 2023 - mdpi.com
Amidst the domestic labor shortage and worldwide pandemic in recent years, there has
been an urgent need for a digital means that allows construction site workers, particularly …
been an urgent need for a digital means that allows construction site workers, particularly …
Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods
Uncertainty estimation is a crucial aspect of deploying dependable deep learning models in
safety-critical systems. In this study, we introduce a novel and efficient method for …
safety-critical systems. In this study, we introduce a novel and efficient method for …
[HTML][HTML] STABC-IR: An air target intention recognition method based on bidirectional gated recurrent unit and conditional random field with space-time attention …
W Siyuan, W Gang, FU Qiang, S Yafei, LIU Jiayi… - Chinese Journal of …, 2023 - Elsevier
The battlefield environment is changing rapidly, and fast and accurate identification of the
tactical intention of enemy targets is an important condition for gaining a decision-making …
tactical intention of enemy targets is an important condition for gaining a decision-making …
Incorporating Different Verbal Cues to Improve Text-Based Computer-Delivered Health Messaging
SR Cox - arXiv preprint arXiv:2404.13633, 2024 - arxiv.org
The ubiquity of smartphones has led to an increase in on demand healthcare being
supplied. For example, people can share their illness-related experiences with others similar …
supplied. For example, people can share their illness-related experiences with others similar …
Crowdsourcing syntactically diverse paraphrases with diversity-aware prompts and workflows
Task-oriented bots (or simply bots) enable humans to perform tasks in natural language. For
example, to book a restaurant or check the weather. Crowdsourcing has become a …
example, to book a restaurant or check the weather. Crowdsourcing has become a …
An extensible and reusable pipeline for automated utterance paraphrases
In this demonstration paper we showcase an extensible and reusable pipeline for automatic
paraphrase generation, ie, reformulating sentences using different words. Capturing the …
paraphrase generation, ie, reformulating sentences using different words. Capturing the …
Say What? Real-time Linguistic Guidance Supports Novices in Writing Utterances for Conversational Agent Training
Writing utterances to train conversational agents can be a challenging and time-consuming
task, and usually requires substantial expertise, meaning that novices face a steep learning …
task, and usually requires substantial expertise, meaning that novices face a steep learning …