Скачать или смотреть Multilingual NLP: #6 | Token Classification using Pretrained Language Models

Token Classification using Pretrained Language Models

In this tutorial, we'll learn how to get True-Word embeddings given Subword embeddings from pretrained language models. As an example, we'll implement the approach for Sentence Transformers model, but the method is generic and could be used with any pretrained language model.

The code used in this tutorial is available here-
https://github.com/makeesyai/makeesy_...

Chapters:
0:00 - Introduction
0:20 - Token and Token Classification Definitions
2:30 - Subword embeddings from Language models
4:40 - Subword embeddings for classification
6:50 - Approaches from Subword to Word embeddings
8:50 - Plan
9:37 - Token embeddings from Sentence Transformers
13:35 - Next

Previous videos in this series-
#5 | Zero-shot Multilingual Text-classification using Pretrained Language Models
   • Multilingual NLP: #6 | Token Classificatio...  

#4 | Real Example Spam Detection using Pretrained Language Models
   • Multilingual NLP: #4 | Real Example - Spam...  

#3 | Train Model for Text Classification using Pretrained Language Model
   • Multilingual NLP: #3 | Train Model for Tex...  

#2 | Create Model for Text Classification using Embedding from Language Models
   • Multilingual NLP: #2 | Create Model for Te...  

#1 | Compute Embeddings from Pretrained Language Models
   • Multilingual NLP: #1 | Compute Embeddings ...  

#zeroshot #multilingual #nlp #token #classification