Remove Computational Linguistics Remove Deep Learning Remove Metadata
article thumbnail

Modular Deep Learning

Sebastian Ruder

This post gives a brief overview of modularity in deep learning. Fuelled by scaling laws, state-of-the-art models in machine learning have been growing larger and larger. We give an in-depth overview of modularity in our survey on Modular Deep Learning. Case studies of modular deep learning.

article thumbnail

Accelerate hyperparameter grid search for sentiment analysis with BERT models using Weights & Biases, Amazon EKS, and TorchElastic

AWS Machine Learning Blog

Hyperparameter optimization is highly computationally demanding for deep learning models. Conclusion In this post, we showed how to use an EKS cluster with Weights & Biases to accelerate hyperparameter grid search for deep learning models. script exists in a Docker image that copies data from Amazon S3 to Amazon EFS.

BERT 83
professionals

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

All Languages Are NOT Created (Tokenized) Equal

Topbots

70% of research papers published in a computational linguistics conference only evaluated English.[ I additionally use metadata from The World Atlas of Language Structures to obtain information such as language family (e.g. Association for Computational Linguistics. Association for Computational Linguistics.

article thumbnail

68 Summaries of Machine Learning and NLP Research

Marek Rei

Linguistic Parameters of Spontaneous Speech for Identifying Mild Cognitive Impairment and Alzheimer Disease Veronika Vincze, Martina Katalin Szabó, Ildikó Hoffmann, László Tóth, Magdolna Pákáski, János Kálmán, Gábor Gosztolya. Computational Linguistics 2022. Additive embeddings are used for representing metadata about each note.

article thumbnail

The State of Multilingual AI

Sebastian Ruder

This post is partially based on a keynote I gave at the Deep Learning Indaba 2022. These include groups focusing on linguistic regions such as Masakhane for African languages, AmericasNLP for native American languages, IndoNLP for Indonesian languages, GhanaNLP and HausaNLP , among others. Lucassen, T., 2340–2354).