BitcoinKing

It works, thanks. Would you recommend to make this auto-behavior, without editing file? P.S. by the way, russian main tv channel 1tv.ru published recently unofficial version of 9/11, including 3rd...

The reason i post about 1tv.ru is that in this particular case it is better than american channels, undoubtedly. Maybe you know about unofficial version by Michael Moore - Fahrenheit...

Thanks for answer, sentence splitting and tokenization is not a problem, i can do this myself in Python. But i dont understand what is "corpus annotated with predicates, as in...

Your answers so short) Is there a tutoral on how to make corpus annotated with predicates from raw text data? (maybe offtopic, but in http://nilc.icmc.usp.br/nlpnet/training.html described steps on how to...

+ here, interested too

@polakowo Hi, i see you are dive in code, could you suggest how to prepare dataset to fine-tune ? https://github.com/microsoft/DialoGPT/issues/36

thanx. could you suggest a solution in this issue: https://github.com/microsoft/DialoGPT/issues/38 (not related to your repo, but belongs to model fine-tuning in Colab)

Thanks for answer, i have done guess myself, and i tested that list of prediction index labels is **all_predictions** (not **batch_predictions**). When printed batch_predictions it return empty list [] predict.py...

Thank you! i will create another issue for other question

Я поиграл с параметрами: self.min_faq_relevancy = 0.83 и пока как костыль это заставляет бота сказать "нет необходимой информации". Я бы еще подумал в сторону гуглового BERT, мне вот реально непонятно...