arXiv subjects

Bryan Anderson

Publications and source records attributed to Bryan Anderson.

2 recordsLinked to original sources

arXiv2025

Understanding the Relationship Between Personal Data Privacy Literacy and Data Privacy Information Sharing by University Students

With constant threats to the safety of personal data in the United States, privacy literacy has become an increasingly important competency among university students, one that ties intimately to the information sharing behavior of these students. This survey based study examines how university students in the United States perceive personal data privacy and how their privacy literacy influences their understanding and behaviors. Students responses to a privacy literacy scale were categorized into high and low privacy literacy groups, revealing that high literacy individuals demonstrate a broader range of privacy practices, including multi factor authentication, VPN usage, and phishing awareness, whereas low literacy individuals rely on more basic security measures. Statistical analyses suggest that high literacy respondents display greater diversity in recommendations and engagement in privacy discussions. These findings suggest the need for enhanced educational initiatives to improve data privacy awareness at the university level to create a better cyber safe population.

cs.CR↗

arXiv2021

On joint training with interfaces for spoken language understanding

Spoken language understanding (SLU) systems extract both text transcripts and semantics associated with intents and slots from input speech utterances. SLU systems usually consist of (1) an automatic speech recognition (ASR) module, (2) an interface module that exposes relevant outputs from ASR, and (3) a natural language understanding (NLU) module. Interfaces in SLU systems carry information on text transcriptions or richer information like neural embeddings from ASR to NLU. In this paper, we study how interfaces affect joint-training for spoken language understanding. Most notably, we obtain the state-of-the-art results on the publicly available 50-hr SLURP dataset. We first leverage large-size pretrained ASR and NLU models that are connected by a text interface, and then jointly train both models via a sequence loss function. For scenarios where pretrained models are not utilized, the best results are obtained through a joint sequence loss training using richer neural interfaces. Finally, we show the overall diminishing impact of leveraging pretrained models with increased training data size.

cs.CL↗