This is a brief summary of paper for me to study and organize it, fairseq: A Fast, Extensible Toolkit for Sequence Modeling (Ott et al., NAACL 2019) that I read and studied.

They introduce the toolkit to make researches and developer to train custom models for translation, summarization, language modeling, and other text generataion task.

The toolkit was written in PyTorch, and demo video can be found below

fairseq Youtube

For detailed introduction, you can found in their paper, fairseq: A Fast, Extensible Toolkit for Sequence Modeling (Ott et al., NAACL 2019) and github

Reference