Transformer from scratch using Multi-30k dataset, pytorch, and SpaCYºº
Attributions to:
The Annotated Transformer https://nlp.seas.harvard.edu/annotated-transformer/#training-loop
Multi30k Dataset English and German data:
@InProceedings{W16-3210, author = "Elliott, Desmond and Frank, Stella and Sima'an, Khalil and Specia, Lucia", title = "Multi30K: Multilingual English-German Image Descriptions", booktitle = "Proceedings of the 5th Workshop on Vision and Language", year = "2016", publisher = "Association for Computational Linguistics", pages = "70--74", location = "Berlin, Germany", doi = "10.18653/v1/W16-3210", url = "http://www.aclweb.org/anthology/W16-3210" }