Search Results for author:
Found 7 papers, 1 papers with code
Learning Disentangled Audio Representations through Controlled Synthesis
This paper tackles the scarcity of benchmarking data in disentangled auditory representation learning.
Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models
Our research demonstrates the significant benefits of using fine-tuning with explanations to enhance the performance of language models.
Learning Disentangled Speech Representations
This benchmark dataset and framework address the gap in the rigorous evaluation of state-of-the-art disentangled speech representation learning methods.
Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction
This study provides an empirical analysis of Barlow Twins (BT), an SSL technique inspired by theories of redundancy reduction in human perception.
Investigating Pre-trained Language Models on Cross-Domain Datasets, a Step Closer to General AI
They all have similar performance and they outperform transformers that are trained from scratch by a large margin.
Opening the Black Box: Analyzing Attention Weights and Hidden States in Pre-trained Language Models for Non-language Tasks
Investigating deep learning language models has always been a significant research area due to the ``black box" nature of most advanced models.
Embedding semantic relationships in hidden representations via label smoothing
Further, we use a new method for analyzing class hierarchy in hidden representations, Neurodynamical Agglomerative Analyisis (NAA), to show that latent class relationships in this analysis model tend toward the relationships of the label vectors as the data is projected deeper into the network.
