Sebastian Ruder

FEBRUARY 23, 2023

For modular fine-tuning for NLP, check out our EMNLP 2022 tutorial. d) Hypernetwork: A small separate neural network generates modular parameters conditioned on metadata. We provide a high-level overview of some of the trade-offs of the different computation functions below. For a more in-depth review, refer to our survey.

Deep Learning 52

Deep Learning NLP Computer Vision Metadata 52

Sebastian Ruder

JUNE 6, 2022

Seeing the emergence of such multilingual multimodal approaches is particularly encouraging as it is an improvement over the previous year’s ACL where multimodal approaches mainly dealt with English (based on an analysis of “multi-dimensional” NLP research we did for an ACL 2022 Findings paper ). Hershcovich et al.

NLP 52

NLP Natural Language Processing Computational Linguistics Neural Network 52

Sebastian Ruder

NOVEMBER 14, 2022

At the same time, a wave of NLP startups has started to put this technology to practical use. I will be focusing on topics related to natural language processing (NLP) and African languages as these are the domains I am most familiar with. This post takes a closer look at how the AI community is faring in this endeavour.

Natural Language Processing 52

Natural Language Processing NLP Computational Linguistics AI 52

Topbots

JUNE 15, 2023

Language Disparity in Natural Language Processing This digital divide in natural language processing (NLP) is an active area of research. 70% of research papers published in a computational linguistics conference only evaluated English.[ Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold.

Natural Language Processing 59

Natural Language Processing Computational Linguistics NLP ChatGPT 59

AWS Machine Learning Blog

MARCH 2, 2023

Sentiment analysis and other natural language programming (NLP) tasks often start out with pre-trained NLP models and implement fine-tuning of the hyperparameters to adjust the model to changes in the environment. She has a technical background in AI and Natural Language Processing.

BERT 75

BERT Deep Learning Metadata Auto-complete 75