Remove Computational Linguistics Remove Computer Vision Remove Neural Network Remove NLP
article thumbnail

NLP Landscape: Germany (Industry & Meetups)

NLP People

Are you looking to study or work in the field of NLP? For this series, NLP People will be taking a closer look at the NLP education & development landscape in different parts of the world, including the best sites for job-seekers and where you can go for the leading NLP-related education programs on offer.

NLP 52
article thumbnail

ML and NLP Research Highlights of 2021

Sebastian Ruder

2021) 2021 saw many exciting advances in machine learning (ML) and natural language processing (NLP). In computer vision, supervised pre-trained models such as Vision Transformer [2] have been scaled up [3] and self-supervised pre-trained models have started to match their performance [4]. Why is it important?  

NLP 52
professionals

Sign Up for our Newsletter

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

article thumbnail

Modular Deep Learning

Sebastian Ruder

For modular fine-tuning for NLP, check out our EMNLP 2022 tutorial. Computation Function We consider a neural network $f_theta$ as a composition of functions $f_{theta_1} odot f_{theta_2} odot ldots odot f_{theta_l}$, each with their own set of parameters $theta_i$. For a more in-depth review, refer to our survey.

article thumbnail

Explainable AI and ChatGPT Detection

Mlearning.ai

Classifiers based on neural networks are known to be poorly calibrated outside of their training data [3]. This methodology has been used to provide explanations for sentiment classification, topic tagging, and other NLP tasks and could potentially work for chatbot-writing detection as well. Attention is not Explanation.

article thumbnail

Selective Classification Can Magnify Disparities Across Groups

The Stanford AI Lab Blog

Across a range of applications from vision 1 2 3 and NLP 4 5 , even simple selective classifiers, relying only on model logits, routinely and often dramatically improve accuracy by abstaining. In Proceedings of the IEEE International Conference on Computer Vision, pp. Selective classification for deep neural networks.