This tutorial shows, how to train a translation model from scratch using Transformer. We will be using Multi30k dataset to train a German to English translation model.
Corresponding pytorch post can be found here.
This notebook is implemented based on github repo of pytorch tutorial. Repo can be found here
If you don't want to run yourself, check this kaggle version of this repo!
KeyBERT is a minimal and easy-to-use keyword extraction technique that leverages BERT embeddings to create keywords and keyphrases that are most similar to a document.
Corresponding medium post can be found here.
This notebook is implemented based on github repo of keyBERT. Repo can be found here
If you don't want to run yourself, check this kaggle version of this repo!
BERTopic is a topic modeling technique that leverages transformers and c-TF-IDF to create dense clusters allowing for easily interpretable topics whilst keeping important words in the topic descriptions.
This notebook is implemented based on github repo of BERTopic. Repo can be found here
If you want to explore through more functionalties of BERTopic. Check this link out
If you don't want to run yourself, check this kaggle version of this repo!
- Multilingual Sentence, Paragraph, and Image Embeddings using BERT & Co.
This notebook is implemented based on github repo of Sentence Transformers. Repo can be found here
If you want to explore through more functionalties of Sentence Transformers. Check this link out
If you don't want to run yourself, check this kaggle version of this repo!