6. nicolas-ivanov/tf_seq2seq_chatbot Sequence-to-sequence model with attention multiple buckets multi-layer recurrent neural network as encoder, and an attention-based decoder https://github.com/nicolas-ivanov/tf_seq2seq_chatbot 8. データと論文 Corpora ・ AlJohri/OpenSubtitles Get a lot of raw movie subtitles (~1.2Gb) ・ Cornell Movie-Dialogs Corpus ~ 40Mb after clearing out the technical data. Papers [1]