3 papers
cs.CL2021
Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification
Varsha Suresh, Desmond C. Ong
Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensi…
cs.CL2021
Using Knowledge-Embedded Attention to Augment Pre-trained Language Models for Fine-Grained Emotion Recognition
Varsha Suresh, Desmond C. Ong
Modern emotion recognition systems are trained to recognize only a small set of emotions, and hence fail to capture the broad spectrum of emotions people experience and express in…
cs.LG2020
Shape-CD: Change-Point Detection in Time-Series Data with Shapes and Neurons
Varsha Suresh, Wei Tsang Ooi
Change-point detection in a time series aims to discover the time points at which some unknown underlying physical process that generates the time-series data has changed. We found…