Uploaded April 2021 | Updated September 2026, 5 hours ago
Part 2 video: youtu.be/P50EHx9DWDM
This is the final video in the NMT series! This time we model training and testing. We also recreate the demo shown and test out some translations.
The previous videos went over some theory behind Neural Machine Translation (NMT), NLP models for sequential data, attention, self-attention, the mT5 model, and the Hugging Face library for transformers.
GitHub repo: github.com/ejmejm/multilingual-nmt-mt5
Colab code: colab.research.google.com/drive/1eGSCod03SjWD_YOfwb33kMJOeDZGu7lP?usp=sharing
Transformer paper: arxiv.org/abs/1706.03762
mT5 paper: arxiv.org/abs/2010.11934
Article on how transformers work: towardsdatascience.com/transformers-141e32e69591
Part 2 video: youtu.be/P50EHx9DWDM
This is the final video in the NMT series! This time we model training and testing. We also recreate the demo shown and test out some translations.
The previous videos went over some theory behind Neural Machine Translation (NMT), NLP models for sequential data, attention, self-attention, the mT5 model, and the Hugging Face library for transformers.
GitHub repo: github.com/ejmejm/multilingual-nmt-mt5
Colab code: colab.research.google.com/drive/1eGSCod03SjWD_YOfwb33kMJOeDZGu7lP?usp=sharing
Transformer paper: arxiv.org/abs/1706.03762
mT5 paper: arxiv.org/abs/2010.11934
Article on how transformers work: towardsdatascience.com/transformers-141e32e69591
