21–30 of 51 posts
Similar offering suite from Microsoft, https://www.microsoft.com/cognitive-services/
I wonder how they compare.
[0] https://www.microsoft.com/cognitive-services/en-us/linguisti...
Accuracy still seems to leave a fair bit to be desired. For example, when parsing "Blue, Brown, Orange, Green and Red Lines were running normally" from this news article [1], "Blue" was interpreted as the color [2], "Brown" was interpreted as the Brown Bears football team [3], "Orange" was interpreted as the Orange Line Washington (not Chicago) Metro [4], "Green" was interpreted as "environmentally friendly" [5], and…
It seemed to run better when I ran it through analyzeEntities: http://pastebin.com/raw/AfXvKAzw
Accuracy still seems to leave a fair bit to be desired. For example, when parsing "Blue, Brown, Orange, Green and Red Lines were running normally" from this news article [1], "Blue" was interpreted as the color [2], "Brown" was interpreted as the Brown Bears football team [3], "Orange" was interpreted as the Orange Line Washington (not Chicago) Metro [4], "Green" was interpreted as "environmentally friendly" [5], and…
You picked a really interesting, and really hard, sentence to use to test us with. It has a couple of interesting phenomena: a reduced conjunction ("Line" goes with each color to make a name, like "Blue Line" even though "Blue" and "Line" are far apart), and high ambiguity ("Green" could be the color, the environmental movement, the political party, one of several people, or lots of other things (https://en.wikipedia.org/wiki/Green_(disambiguation) ).
These are hard! So hard, in fact, that I'm reasonably sure that there's no system in existence that would get these ones right. (I hope I'm wrong, actually, I'd love to see approaches that can solve problems like this generally.)
Our systems are state-of-the-art, or in some cases better than any other published system. But language is really hard, and even the world's best systems are way worse than any human at understanding language. That's what makes working on this stuff so much fun and so challenging. It feels so easy for us as humans, but we just haven't figured out how to model all this so that the computers can do as well.
(I'm going to steal this sentence to use internally as a great "NLP is hard" example, thanks!)
Accuracy still seems to leave a fair bit to be desired. For example, when parsing "Blue, Brown, Orange, Green and Red Lines were running normally" from this news article [1], "Blue" was interpreted as the color [2], "Brown" was interpreted as the Brown Bears football team [3], "Orange" was interpreted as the Orange Line Washington (not Chicago) Metro [4], "Green" was interpreted as "environmentally friendly" [5], and…
Hmm, which NLP request did you run it as? It seemed to run better when I ran it through analyzeEntities: http://pastebin.com/raw/AfXvKAzw
On the other side of the NLP spectrum, what players out there are involved in NLG (natural language generation)? I've seen Arria and a couple other small projects, but I'm just starting to investigate the space and haven't found a whole lot yet.
Our initial aim is to index the whole Wikipedia and have pre-generated NLG for all pages as additional info for better searches.
Right now we are using Lucene & Syntaxnet but I haven't found a good library for hierarchical clustering of text
Check us out at www.shoten.xyz
Accuracy still seems to leave a fair bit to be desired. For example, when parsing "Blue, Brown, Orange, Green and Red Lines were running normally" from this news article [1], "Blue" was interpreted as the color [2], "Brown" was interpreted as the Brown Bears football team [3], "Orange" was interpreted as the Orange Line Washington (not Chicago) Metro [4], "Green" was interpreted as "environmentally friendly" [5], and…
Google Research PM here -- my team built the language understanding tech that powers the API. Thanks for checking it out! You picked a really interesting, and really hard, sentence to use to test us with. It has a couple of interesting phenomena: a reduced conjunction ("Line" goes with each color to make a name, like "Blue Line" even though "Blue" and "Line" are far apart), and high ambiguity ("Green" could be the co…
It says 'train line' right in that sentence. Where is the ambiguity?
even if it missed that why didn't any of the 'cta' , 'chicago' , 'train', 'run' or 'line' nudge it in the right direction. It seems to have identified 'cta' entity correctly but completely ignored that context for the next words in the sentence.
I'm curious to see whether clients actually want to move very large datasets through these APIs, or whether that's too costly. It strikes me that cloud services work best for data generated and managed in the same cloud...
I guess for data that is generated on site it's a net negative, but I'd guess almost all data has to go across the internet at some point and google is probably not the worst warehouse on that highway.
Earlier quoted context omitted.
Why would you need the Speech API if you already have a known-good transcript?
I'm sorry if I was unclear. If I used the Cloud Speech API to produce the transcript, is there another library/service/etc that would align it to the original audio again.
So how long until these new services get summarily discontinued?
They include a deprecation policy.
Earlier quoted context omitted.
Google Research PM here -- my team built the language understanding tech that powers the API. Thanks for checking it out! You picked a really interesting, and really hard, sentence to use to test us with. It has a couple of interesting phenomena: a reduced conjunction ("Line" goes with each color to make a name, like "Blue Line" even though "Blue" and "Line" are far apart), and high ambiguity ("Green" could be the co…
>"Green" could be the color, the environmental movement, the political party, one of several people, or lots of other things It says 'train line' right in that sentence. Where is the ambiguity? even if it missed that why didn't any of the 'cta' , 'chicago' , 'train', 'run' or 'line' nudge it in the right direction. It seems to have identified 'cta' entity correctly but completely ignored that context for the next wor…
That's the thing -- in your (wetware) mind it says "train line." But the sentence itself it just says "line", which can mean a whole much of things.