Are all these Amazon stories from re:Invent? Would it make sense to combine them into a single index today?
Amazon Lex – Build Conversational Voice and Text Interfaces
51–56 of 56 posts
Re: Amazon Lex – Build Conversational Voice and Text Interfaces
#52It's great to see so much competition in this space. This initial offering looks limited in its ability to handle more complex branching and context building but hopefully it will evolve. I'm also a little surprised at the pricing given that Google and Facebook offer comparable services for free.
Re: Amazon Lex – Build Conversational Voice and Text Interfaces
#53Earlier quoted context omitted.
I'm working for a startup called Boost.ai where we have decided to build our own deep learning model and create our own training data. We use several models that predicts what word comes next, take care of mispellings and dialects. We also have memory so it can remember contexts when you ask a new question or it predicts that you want to start with a new context. If you want something kick ass, I highly recommend bui…
Any pointers on where to get started? I've messed with Karpathy's RNN example using Shakespeare and PG essays, but don't know where to go from there.
https://github.com/larspars/word-rnn
RNN is great approach if you want to play around with text generation with deep learning. But for a chatbot, deep learning alone is not there yet. We create our own intents based on the domain and predict the intent of each question. We have also made it looks smarter by creating an intent hierarchy where we try to do multiple predictions for a question with a goal to drill the question down in the intent tree. In that way we know that the question is about a bank card and can figure out if you want a new one, block it, increase credit, set limits and so on.
Re: Amazon Lex – Build Conversational Voice and Text Interfaces
#54Earlier quoted context omitted.
The "Ok Google/Google Now" voice interactivity (or whatever the official name is) on Android phones is much better than Amazon's Alexa/Echo. It actually remembers context from sentence to sentence so you can say "What is the population of Chicago" and it will answer. Then you can say, "How long would it take me to drive there?" And it understands that you are still talking about Chicago. Every interaction with Alexa…
There's nothing about Alexa's API that would prevent doing that, it already has the concept of a conversation and I think we'll see raid improvement in how people make use of that.