Search Results for author:
Found 7 papers, 5 papers with code
The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition
The promise of ICL is that the LLM can adapt to perform the present task at a competitive or state-of-the-art level at a fraction of the cost.
A Multi-Perspective Machine Learning Approach to Evaluate Police-Driver Interaction in Los Angeles
Interactions between the government officials and civilians affect public wellbeing and the state legitimacy that is necessary for the functioning of democratic society.
Using Emotion Embeddings to Transfer Knowledge Between Emotions, Languages, and Annotation Formats
In this work, we study how we can build a single model that can transition between these different configurations by leveraging multilingual models and Demux, a transformer-based model whose input includes the emotions of interest, enabling us to dynamically change the emotions predicted by the model.
Leveraging Label Correlations in a Multi-label Setting: A Case Study in Emotion
First, we develop two modeling approaches to the problem in order to capture word associations of the emotion words themselves, by either including the emotions in the input, or by leveraging Masked Language Modeling (MLM).
VAuLT: Augmenting the Vision-and-Language Transformer for Sentiment Classification on Social Media
VAuLT is an extension of the popular Vision-and-Language Transformer (ViLT), and improves performance on vision-and-language (VL) tasks that involve more complex text inputs than image captions while having minimal impact on training and inference efficiency.
CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks
Existing CL benchmarks have facilitated research on task adaptation and mitigating "catastrophic forgetting", but are limited to vision-only and language-only tasks.
End-to-end Generative Zero-shot Learning via Few-shot Learning
In this work, we introduce Z2FSL, an end-to-end generative ZSL framework that uses such an approach as a backbone and feeds its synthesized output to a Few-Shot Learning (FSL) algorithm.
