Custom Classifier on Top of Bert-like Language Model
Take pre-trained language model and build custom classifier on top of it.
Taking existing pre-trained language model and understanding it’s output - here I use PolBERTa trained for Polish language.
Building custom classification head on top of the LM.
Using fast tokenizers to efficiently tokenize and pad input text as well as prepare attention masks.
Preparing reproducible training code with PyTorch Lightning.
Finding good starting learning rate for the model.
Validating the trained model on PolEmo 2.0 dataset (benchmark for Polish language sentiment analysis with 4 classes).
Don't forget to tag
in your comment, otherwise they may not be notified.
Data Engineer / Machine Learning Engineer @ Egnyte
Share this project
Transformers - Hugging Face
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
The Illustrated BERT, ELMo, and co.
How NLP cracked transfer learning.
Evolution of Representations in the Transformer
The evolution of representations of individual tokens in Transformers trained with different training objectives (MT, LM, MLM - BERT-style).
Sized Fill-in-the-blank or Multi Mask filling with RoBERTa
Sized fill-in-the-blank or conditional text filling is the idea of filling missing words of a sentence with the most probable choice of words.
Share what you've made with ML.