Live data from Hacker News

How Alexa knows “peanut butter” is one shopping-list item, not two

developer.amazon.com

81–90 of 147 posts

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#81

What about "peanut butter cookies"?

Homer: "Alexa, please order: peanut, butter cookie, d'oh!"

in that case you'd get peanut, butter cookie, and dough, so i suppose you could make a peanut and butter cookie bread. lol.

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#82
post #76
post #66

Earlier quoted context omitted.

Yes, they do. There's evidence to suggest that punctuation marks were devised as pronunciation guides, indicating how to inflect and when to pause, rather than syntactic markers in their own right. Commas in particular indicate a distinctive inflection and short pause in speaking; such would be detectable by Alexa especially if it uses a neural net or similar to analyze human speech.

That was not the point of what I said at all. It Could interpret the vocal cues, yes. As far as I know this is still not a solved problem for speech to text, and results going the other way and trying to guess punctuation is still more reliable. Back to what I really was getting at: I'm pretty sure the person I replied to was suggesting Alexa could just split(',') and call it a day. With text, yes. With voices this w…

No, i'm suggesting:

- ignore the comma, point and space as delimiter and compare the values / entities against a dictionary for neighbouring words.

- don't ignore the comma and compare the values against a dictionary.

Put a priority ( or in machine learning terms: a classifier) on both outcomes, because comma is not reliable in spoken language. So that it would interprit peanuts butter as [peanuts, butter] and peanut butter as [peanut butter].

PS. Now i hope that text-to-speech translates spoken: peanuts correctly to [peanuts] and not [peanut], because that would fail.

PS2. The article itselve doesn't mention the punctuation problem

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#85
post #83

How come we are doing so much with machine learning but we still have situations like "You have 1 things in your shoping wagon"

I think the explanation there is as simple as "there are lots of different people." I can't write software half as well as a significant percentage (maybe a majority) of HN users, but the average person can't write software half as well as me.

Of course, I could just be dead wrong. I'm just conjecturing while I procrastinate.

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#86
post #76

Earlier quoted context omitted.

That was not the point of what I said at all. It Could interpret the vocal cues, yes. As far as I know this is still not a solved problem for speech to text, and results going the other way and trying to guess punctuation is still more reliable. Back to what I really was getting at: I'm pretty sure the person I replied to was suggesting Alexa could just split(',') and call it a day. With text, yes. With voices this w…

No, i'm suggesting: - ignore the comma, point and space as delimiter and compare the values / entities against a dictionary for neighbouring words. - don't ignore the comma and compare the values against a dictionary. Put a priority ( or in machine learning terms: a classifier) on both outcomes, because comma is not reliable in spoken language. So that it would interprit peanuts butter as [peanuts, butter] and peanut…

>PS2. The article itselve doesn't mention the punctuation problem

It doesn't go into detail but it does seem to mention it.

>Off-the-shelf broad parsers are intended to detect coordination structures, but they are often trained on written text with correct punctuation. Automatic speech recognition (ASR) outputs, by contrast, often lack punctuation, and spoken language has different syntactic patterns than written language.

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#87
post #56

I'm pretty sure you could do this in a standard LALR(1) grammar and give [peanut butter] precedence over [peanut] [butter].

You would need to look ahead recursively as different word orders may be acceptable in a human language. Not all languages are like French.

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#88
post #62

In text parsing, this whole machine learning would be implemented as "ignore white space as delimiter" ( that's how I implemented it on one of my projects) Ps. I'm aware this will not be a popular comment

Sentences spoken aloud don't have commas.

Or pauses between words

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#89
post #16

This, yet again shows just how far the computer science is from real natural language processing, despite of all "AI" companies' claims. Unless they have all and everything hardcoded, even such natural thing are impossible to process for the "natural" language processing programs. All cloud "AI" and "natural" language processing services should really be called "lots and lots of hardcoded stuff language processing"

That is literally the opposite of what this article says.

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#90
I recently heard about a book called "Anything You Want" and wanted to add it to my shopping list. I tried repeatedly saying "Alexa, add 'Anything You Want' book to my shopping list" and every variation thereof. Alexa was unable to add that book title no matter what I tried.
Post reply on HN