Scholar
Julia Ive
Google Scholar ID: WMYcG5EAAAAJ
University College London
Citations & Impact
Citations
786
H-index
14
i10-index
19
Publications
20
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- - Safe Training with Sensitive In-domain Data: Leveraging Data Fragmentation To Mitigate Linkage Attacks
- - Source Code is a Graph, Not a Sequence: A Cross-Lingual Perspective on Code Clone Detection
- - Classifying Social Media Users Before and After Depression Diagnosis via their Language Usage: A Dataset and Study
- - Using Large Language Models (LLMs) to Extract Evidence from Pre-Annotated Social Media Data
- - Embracing the uncertainty in human-machine collaboration to support clinical decision making for Mental Health Conditions
- - Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint
- - Leveraging the potential of synthetic text for AI in mental healthcare
- - SURF: Semantic-level Unsupervised Reward Function for Machine Translation
- - Modeling Disagreement in Automatic Data Labelling for Semi-Supervised Learning in Clinical Natural Language Processing
- - Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translation
- - Generation and evaluation of artificial mental health records for Natural Language Processing
- - Distilling Translations with Visual Awareness
Research Experience
- Conducts research in areas like mental health and legal data using Large Language Models (LLMs); applies Reinforcement Learning methods to LLMs; explores Bayesian Deep Learning techniques to enhance model decision-making transparency.
Background
- Research interests include ethical aspects of human-AI collaboration, such as bias, privacy, and transparency; focusing on developing text rewriting techniques for normalizing, de-biasing, and de-identifying text to build responsible AI models that protect sensitive individual information.
Miscellany
- Participates in discussions about the future direction of AI governance structures; represents the Responsible AI UK project at international conferences.
