deep-learning

A Relation-Specific Attention Network for Joint Entity and Relation Extraction

Joint extraction of entities and relations is an important task in natural language processing (NLP), which aims to capture all relational triplets from plain texts. This is a big challenge due to some of the triplets extracted from one sentence may …

One-Shot Neural Architecture Search via Novelty Driven Sampling

One-Shot Neural architecture search (NAS) has received wide attention due to its computational efficiency. Many One-Shot NAS methods use the validation accuracy based on the supernet as the stepping stone to search the best performing architecture …

Overcoming Multi-Model Forgetting in One-Shot NAS with Diversity Maximization

One-Shot Neural Architecture Search (NAS) significantly improves the computational efficiency through weight sharing. However, this approach also introduces multi-model forgetting during the supernet training (architecture search phase), where the …

Cost-sensitive parallel learning framework for insurance intelligence operation

Recent advancements in artificial intelligence (AI) are providing the insurance industry with new opportunities to create tailored solutions and services based on newfound knowledge of consumers, and the execution of enhanced operations and business …

Cross-domain deep learning approach for multiple financial market prediction

Over recent decades, globalization has resulted in a steady increase in cross-border financial flows around the world. To build an abstract representation of a real-world financial market situation, we structure the fundamental influences among …

Network Embedding

Information network mining often requires examination of linkage relationships between nodes for analysis. Recently, network representation has emerged to represent each node in a vector format, embedding network structure, so off-the-shelf machine learning methods can be directly applied for analysis.

Deep Structure Learning for Cyberbullying Detection on Social Networks

This project aims to build a deep structure learning system to detect cyberbullying on social networks to improve the e-safety for children and young people. Detailed research topics include a deep node representation model, a deep-signed link prediction approach, and a multi-task cyberbullying detection algorithm. The outcomes will not only lay the theoretical foundations for building intelligent systems on social networks by integrating multiple view information such as user profiles, network structures, and text messages, but could be also used by public sectors to detect cyberbullying, thus improving e-safety for children.