41–45 of 45 posts
Earlier quoted context omitted.
Hi! Thanks for the reply! One more quick one. :) Are the "time" entities relative or absolute time or either?
We normalize relative times so that they're absolute. So, "remind me to marinate the chicken in 2 hours" will get normalized to 6:00 PM (assuming it's being said at 4:00 PM)
Earlier quoted context omitted.
It's not compatible with any of my devices, a Galaxy Nexus and a Transformer Prime. Any idea why?
What country are you in? We're currently only available in Canada and the US but we're expanding very soon.
I guess everybody agrees, nowadays entering commands to any kind of machine is still much more accurate and quicker if you use your hands for doing so.
This said, i think the technologies is in particular useful in situations in which you are not able to use your hands. This could be for example because you are busy working or you are handicapped. So one idea which comes to my mind would be an assistant for handicapped people, e.g. a device which can be used to control an electric wheelchair.
Earlier quoted context omitted.
You'd be a whole lot better of saying you've written a natural-language interface to a number of search domains. You're promising a lot by claiming to have an API that not only accomplishes understanding (which, contrary to your claim, is reserved for much deeper and more structured inferences than what you're providing here -- are you transforming sentences into a formal language before feeding it to epicurious, or…
I agree. I took the headline as a hypothetical question. The system described is the most pragmatic of natural language processing systems, a lovely term that just means the input is natural language and there is some processing. I'm optimistic, by the way, and think that though "objective" word meaning is a cognitive illusion, we will crack the code within the next 20 years. But there is nothing on the forefront of…
Earlier quoted context omitted.
I agree. I took the headline as a hypothetical question. The system described is the most pragmatic of natural language processing systems, a lovely term that just means the input is natural language and there is some processing. I'm optimistic, by the way, and think that though "objective" word meaning is a cognitive illusion, we will crack the code within the next 20 years. But there is nothing on the forefront of…
I hate to make this discussion religious but NLU is widely used in industry to refer to systems such as ours. Daniel Jurafasky a professor at Stanford well known in industry uses NLU on page 822 chapter 24 of the book "Speech and Language Processing" to refer to a hypothetical frame and slot system very similar to what we have built. A quick search for Natural Language Understanding on google scholar will yield numer…