AI Research Review - Spelling and ASR
This week’s AI Research Review is Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems.
Taufiquzzaman Peyash
Deep Learning Engineer at AssemblyAI
Deep Learning Paper Recap - Language Models
This week’s Deep Learning Paper Recap is Prune Once For All: Sparse Pre-Trained Language Models
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
This paper falls in the category of parameter efficient fine-tuning, where the goal is to use as few parameters as possible to achieve almost the same accuracy as if we were to fine-tune the whole model.
Text Segmentation - Approaches, Datasets, and Evaluation Metrics
In this post, we give an overview of the best approaches, datasets, and evaluation metrics commonly used for the task of Text Segmentation.