Post Transformers-2020: Great Start in 2021
Transformers evolution at the beginning of 2021: impressive achievements with Zero-Shot image classification and Switch Transformers. ... Read More
transformers
Zero-Shot Image Classification – CLIP
Zero-shot text classification appeared last year and was a pretty cool thing. At the beginning of this year, we have an implementation of zero-shot image classification. What a beginning of the year :-) ... Read More
txtai – Low-Code Semantic Search with Transformers
A very brief introduction to fastai: transformers based Python library for fast semantic QA and zero-shot classification. ... Read More
Spark NLP: Accuracy and Scalability
Another, indystry focused NLP player, accurate, scalable and multilangual. ... Read More
QuantumStat: NLP on Steroids
Introduction Anather post related to NLP and transfer-learning paradigm. Since at least in the after-BERT era it is not preferable to train your own model for anything related to NLP, the normal way of doing things is: Find a model that is already fine-tuned for your purpose, and Use it, ... Read More
HuggingFace Impresses Again. No Need for Fine-Tuning.
With the latest HuggingFace BERT based transformers, it is possible to implement text classification against arbitrarily chosen set of categories. ... Read More
AdapterHub: New Kid on the Block for Transfer Learning
Introduction First, there was a BERT, at least all of this started with it. It is a general-purpose language model, once pre-trained for different languages and in different size variations. If you wanted to use it for some specific task, you should fine-tune it in a way that you take ... Read More