Multi-turn dialogue using dialoGPT

[anthonyralston]

I am looking to use dialoGPT-large on the Hosted Inference API for a chatbot demo but am having trouble generating decent multi-turn dialogue.

As an example, when I post the following to the API endpoint:

I heard you won the cricket match. <|endoftext|> I did! <|endoftext|> Awesome. Who did you play against? <|endoftext|> I played against the Aussies. <|endoftext|> Wow ! Was it a tough game? <|endoftext|> It was a tough game. It went on till the last over. They almost won. <|endoftext|> Where was the match? <|endoftext|>

It seems to just spit it back out at me:

I heard you won the cricket match. <|endoftext|> I did! <|endoftext|> Awesome. Who did you play against? <|endoftext|> I played against the Aussies. <|endoftext|> Wow ! Was it a tough game? <|endoftext|> It was a tough game. It went on till the last over. They almost won. <|endoftext|> Where was the match? <|endoftext|>

This blog post has an example of someone getting meaningful results from exactly the above prompt: https://medium.com/datadriveninvestor/a-simple-contextual-chatbot-to-predict-an-reply-with-pre-trained-dialogpt-model-from-huggingface-f681b550cd60.

Any guidance as to where I’m going wrong would be really appreciated.

[srush]

@julien-c Any idea here? I think we might need some way to force dialogues to continue at least one more turn?

[julien-c]

Hard to know without debugging this particular model.

You could try checking out our recently merged ConversationalPipeline (merged from https://github.com/huggingface/transformers/pull/5516 and contributed by @guillaume-be)

(will expose through the hosted API at some point)