Live data from Hacker News

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

developer.amazon.com

21–30 of 147 posts

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

#21
post #5

The German language is superior in this regard because there it would we either "peanut, butter" or "peanutbutter".

It would be easier in languages that make use of a high degree of inflection, especially in Slavic languages, where - that's unusual in other language families - declension also depends on whether the word is a noun or an adjective.

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

#24
post #2

Because who orders a single peanut.

Well this is not the key indicator. The key indicator is the absence of pause between the words, that's how we differentiate between "peanut butter" and "peanut, butter".

Far more important than the lack of a pause between then words is the a priori fact that "peanut butter" is a common single item and "peanut, butter" is an uncommon list of items. It is that fact that means that you require a pause between the words to indicate "peanut, butter".

If you ordered "butter, peanuts" for example, it would probably get that it was two items even without the pause between words.

It's all about the prior probabilities.

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

#25
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"

State of the art virtual assistants offer little intelligence over a command line interface, except instead of typing the command line in, you say it. Besides that, not much difference; the syntax is rigid and the computer doesn't understand your utterance more intelligently than GCC understands "gcc -o my_prog my_prog.c".

It would be interesting if AI assistants were described honestly in this manner as a "spoken command line interface" instead of as equivalent to human speech recognition.

AI is mechanical turks all the way down.

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

#26
post #9

What about "peanut butter cookies"?

There's only one way to find out.

Reminds me of the time I tested a web shop's ordering form for a a paper catalogue, using a colleague's real address. He got something in the mail a few weeks later...

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

#27

Earlier quoted context omitted.

Well this is not the key indicator. The key indicator is the absence of pause between the words, that's how we differentiate between "peanut butter" and "peanut, butter".

Far more important than the lack of a pause between then words is the a priori fact that "peanut butter" is a common single item and "peanut, butter" is an uncommon list of items. It is that fact that means that you require a pause between the words to indicate "peanut, butter". If you ordered "butter, peanuts" for example, it would probably get that it was two items even without the pause between words. It's all abo…

I would disagree here. Especially in the context of a shopping list.

If I were to say 'peanut' 'butter' my interlocutor would probably interrupt me to ask for confirmation because that would be enough to create doubt.

'Peanut' and 'butter' are two unrelated words and it is the absence of pause that creates a pseudo single word.

Pauses are extremely important in spoken language and should be exploited.

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

#28
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"

State of the art virtual assistants offer little intelligence over a command line interface, except instead of typing the command line in, you say it. Besides that, not much difference; the syntax is rigid and the computer doesn't understand your utterance more intelligently than GCC understands "gcc -o my_prog my_prog.c".

My girlfriend routinely asks questions with convoluted grammar and gets a relevant response much of the time. I'm always amazed when it happens.

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

#29

Earlier quoted context omitted.

Far more important than the lack of a pause between then words is the a priori fact that "peanut butter" is a common single item and "peanut, butter" is an uncommon list of items. It is that fact that means that you require a pause between the words to indicate "peanut, butter". If you ordered "butter, peanuts" for example, it would probably get that it was two items even without the pause between words. It's all abo…

I would disagree here. Especially in the context of a shopping list. If I were to say 'peanut' 'butter' my interlocutor would probably interrupt me to ask for confirmation because that would be enough to create doubt. 'Peanut' and 'butter' are two unrelated words and it is the absence of pause that creates a pseudo single word. Pauses are extremely important in spoken language and should be exploited.

If we’re assuming human level AI, maybe and not even then. Nonnative English speakers from languages without a singular/plural distinction often make use singulars where a plural is called for.

Domain knowledge around the intent (making a shopping list) and around language conventions helps a lot, not only for NLU, but also for NLS.

But even without a huge NLU dictionary, a simple MC or CRF segmentation model would work. As said earlier, almost no one says., “Add peanut to the shopping list.” They say, “Add peanuts”, of if they’re very atypical, “Add a peanut”. A bare “peanut” is simply unlikely.

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

#30

Earlier quoted context omitted.

Far more important than the lack of a pause between then words is the a priori fact that "peanut butter" is a common single item and "peanut, butter" is an uncommon list of items. It is that fact that means that you require a pause between the words to indicate "peanut, butter". If you ordered "butter, peanuts" for example, it would probably get that it was two items even without the pause between words. It's all abo…

I would disagree here. Especially in the context of a shopping list. If I were to say 'peanut' 'butter' my interlocutor would probably interrupt me to ask for confirmation because that would be enough to create doubt. 'Peanut' and 'butter' are two unrelated words and it is the absence of pause that creates a pseudo single word. Pauses are extremely important in spoken language and should be exploited.

I think the catch is that human detection of pauses is far more fraught with difficulty than you'd imagine. Overly emphasized pauses are easy to discern, but quite a lot of speech pulls words far closer together than you would think. And this is just in english. Not all languages work with emphasis syllables and such.
Post reply on HN