Semantic search in 2020: the BERT way
Description of how to implement semantic search over large text corpora, running on your local laptop. ... Read More
NLP
Natural Language Processing. Chatbots, text generators, etc.
UnifiedQA – You Have Some Question Maybe?
Need a system that would answer to your questions asked in different formats? UnifedQA is the keyword. ... Read More
Spark NLP: Accuracy and Scalability
Another, indystry focused NLP player, accurate, scalable and multilangual. ... Read More
GPT-3 Overhyped
As from the very beginning, when it apears, GPT-3 is producing hype. And with a reason: it is the most advanced language model ever built. But, is it overyped? Researchers at Nabla, an AI-enabled healthcare platform, found that GPT-3 lacks the logical reasoning skills to be a useful medical chatbot.What ... Read More
A Great Mentor Notes
“If you think about the most valuable advice I’ve ever gotten from a mentor, it was this: if you’re going to be a coach in any capacity, just make a commitment. Because it takes a lot of work to be good at something you love. You can learn a lot ... 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
Zero-Shot Text Classification
Introduction: The stone-age AI Era In the beginning, in the AI stone-age era, you take several thousands of observations and train an old-style fully-connected neural network, And, if you were happy, you would have something useful. That time of training our own neural networks is done a long time ago, ... 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
History Lessons From Parallel Universes
Few fictction history lessons, autogenerated by GPT-2. ... 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