3

One 'easy' way would be to have some sort of conversational memory, where you track what the user has said already. I don't know how complex your patterns are, but if you could recognise names and track references, you could try and build up a mental model of the user's relationships with other people, and perhaps refer to that in your bots responses. The ...


2

The former: build and train a model first, and then think about the user interface. Effectively, a chatbot is a user interface to your model. If you run it 'off-line' on input text and it works, then you have achieved your goal without the added complexity of driving a conversation (which is harder than one might think). Also, building an 'abstract' ...


1

They're all important. NLP is an umbrella term that includes the other two; NLG is only concerned with generating language, ie transforming some internal data structure into human language. NLU is about processing information contained in language, and putting it into relation with a knowledge base etc. If you don't know anything about any of these fields, ...


1

I have not found one other than scraping a few pages from Urban Dictionary, I built my list via crowdsourced style and got a number of interesting words I had not considered. Start with the worst words you can think of, then try slang and accidental or on purpose misspellings of them


1

Recognising intents is only a small step in developing a chatbot. It's fine to use an ML classifier with training data for that, no need to keep the original list of intents. However, you should really think about the next step: how are you getting your bot to conduct a dialogue, rather than firing off single responses to user queries. That is where things ...


1

I think it's a real bot. I've seen people talking about how it's rendering has improved over time and they claimed that was an improvement in the Motion Capture suit. I think that's simply because the program has improved over time. Imagine YOU created AI Angel (assuming it's really AI), would you be more worried about it's functionality or it's realism ...


1

It's pretty easy to tell what's going on with AI Angel Angelica. If you've watched some of the videos, you'll notice the steady progression of the real-time rendering. The first videos were really jittery and there were a lot of movements (awkward mouth movements, fingers unable to move, etc) to the more recent ones with realistic-ish mouth movements and ...


Only top voted, non community-wiki answers of a minimum length are eligible