Show HN: We've developed a Natural Language API
11–18 of 18 posts
Re: Show HN: We've developed a Natural Language API
#12Very cool, but I find it strange that all of the example phrases on the demo page are much longer than recommended by the API docs (<10 words). Why is this?
Re: Show HN: We've developed a Natural Language API
#13Very cool, but I find it strange that all of the example phrases on the demo page are much longer than recommended by the API docs (<10 words). Why is this?
9 or 10 words is about the average sentence that we receive, it is just a guideline so that users understand that we aren't going to handle multiple sentences or paragraphs.
Re: Show HN: We've developed a Natural Language API
#14Re: Show HN: We've developed a Natural Language API
#15Earlier quoted context omitted.
9 or 10 words is about the average sentence that we receive, it is just a guideline so that users understand that we aren't going to handle multiple sentences or paragraphs.
Right; the more important thing is that they all have a single intent.
What happens when you encounter phrases with multiple intents? Is it something you can detect but is difficult to deal with, or is it a best-guess kind of thing where you attempt to obey the "first intent"? Or something else?
Re: Show HN: We've developed a Natural Language API
#16Wow, this is pretty cool! Could you give a few more examples to get a feel for what kind of results you get (and inputs you can give)?
Take a look at our ruby specs: https://github.com/Maluuba/napi-ruby/blob/master/maluuba_nap... There's nearly a hundred sample sentences and expected outputs -- and they all pass :)
Re: Show HN: We've developed a Natural Language API
#17Dude this is amazing, I want to try it for printavo