Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How would you use an accurate Natural Language Understanding (NLU) API?

maluu.ba

Post reply on HN
Print view View original

11–20 of 45 posts

Re: How would you use an accurate Natural Language Understanding (NLU) API?

#11

Post by hooande »

languagehacker wrote: post #9

From what I read, I don't really see a robust NLU engine here. I see a probabilistic transformation engine (maybe bootstrapped with some linguistic data structures) that identifies 7 buckets and then rephrases the query or request into a format better suited to achieve the desired result in that engine. This isn't too far from saying that you have a search engine that "knows" how to answer questions, because you have…

They didn't say that they invented general intelligence. This is clearly providing a natural language interface to an existing api. It doesn't take degrees in neuroscience and philosophy to do that.

They've clearly spent a lot of time to build a working product. You reacted to only a few words from the page title. It's easy to read books on the theory of intelligence, much harder to make a contribution by trying to solve a real problem.

Re: How would you use an accurate Natural Language Understanding (NLU) API?

#12

Post by pdat »

fatbat wrote: post #10

I am interested in the calendar + reminder domain of it. More so if it works offline (ie- Soundhound/Shazam app). Can you elaborate on the calendar domain?

hi,

Well currently we support 4 actions within calendar, "CREATE_EVENT", "SEARCH_CALENDAR", "MODIFY_EVENT" and "DELETE_EVENT". There are a number of different entities including "dateRange, lengthOfTime, timeRange, date, time, meetingTopic, contactName, friendOrRelative, location, originalTime, originalDate, originalLocation, replacementTime, replacementDate" and a few others I'm sure I've missed.

For reminder we support "CREATE_REMINDER" and "SEARCH_REMINDER", we also support the entities "message", "time" and "arrivalLocation" and "leaveLocation". Does this answer your question or did you want a more specific answer? If you want more information feel free to email us directly :) .

Re: How would you use an accurate Natural Language Understanding (NLU) API?

#13

Post by jpantony »

languagehacker wrote: post #9

From what I read, I don't really see a robust NLU engine here. I see a probabilistic transformation engine (maybe bootstrapped with some linguistic data structures) that identifies 7 buckets and then rephrases the query or request into a format better suited to achieve the desired result in that engine. This isn't too far from saying that you have a search engine that "knows" how to answer questions, because you have…

I feel that you have misunderstood what we have here. I agree that "true" understanding requires is almost an impossible problem to solve due to the fact that it requires context that is only available to the individual. However that level of understanding is not really necessary for applications today. What we are aiming to provide is a system that will allow developers to have natural language queries as their input and have all the pieces of information required for their application extracted. Secondly, the name "natural language understanding" is given to a large area of computer science ranging from sentiment analysis to information extraction. Many of the areas do not even involve deep understanding of contextual meaning in the way you describe. That however does not diminish the importance of any of these fields nor does it eliminate them from the the umbrella of natural language understanding.

Re: How would you use an accurate Natural Language Understanding (NLU) API?

#15

Post by jpantony »

vhf wrote: post #5

I cannot answer your question -- I have no idea. (edited : well, why not for "customer service", along with the traditional FAQ ? Or use it instead of the useless "solve this problem" useless multiple choice walkthrough in Windows or such ? ) But I upvoted because I really liked to discover this company, what it does, and more importantly how it does it. Thanks for the clear examples and output provided !

Thank you for your up-vote :)

Re: How would you use an accurate Natural Language Understanding (NLU) API?

#16

Post by ChuckMcM »

hooande wrote: post #11
languagehacker wrote: post #9

From what I read, I don't really see a robust NLU engine here. I see a probabilistic transformation engine (maybe bootstrapped with some linguistic data structures) that identifies 7 buckets and then rephrases the query or request into a format better suited to achieve the desired result in that engine. This isn't too far from saying that you have a search engine that "knows" how to answer questions, because you have…

They didn't say that they invented general intelligence. This is clearly providing a natural language interface to an existing api. It doesn't take degrees in neuroscience and philosophy to do that. They've clearly spent a lot of time to build a working product. You reacted to only a few words from the page title. It's easy to read books on the theory of intelligence, much harder to make a contribution by trying to s…

I am sure they are earnest in their efforts, I chuckled when I read "Some of our engineers have been working on this problem for two years, ..." because I know engineers who have been working on that problem for 20 years and they still haven't got it right. One of them (at Intel in the '80s) had a poster that said "Time flies like an Arrow, Fruit Flies like a Banana." which captured the challenge for him. One of the founders of Android, Rich Miner, was an Amiga guy that I knew peripherally through the developers network. He did a company called WildFire which was an assistant that would be on the phone with you that you could ask things of or make requests too. Also felt the problem space was huge, then there were no less than three Phd's at Google who gave a tech talk on the Goog-411 project where they were listening to people ask for phone numbers and trying to figure out what number they were looking for. (one domain of questions so almost like cheating).

Perhaps they just write optimistically, I am excited to seem them working on the problem (I'd suggest they search blekko since we can add slashtags and do better domain search but that is just me). Having seen the folks who have run at this problem and been knocked on their backsides I have tremendous respect for taking on a really really hard problem. Can't wait for the beta.

Re: How would you use an accurate Natural Language Understanding (NLU) API?

#17

Post by fatbat »

pdat wrote: post #12
fatbat wrote: post #10

I am interested in the calendar + reminder domain of it. More so if it works offline (ie- Soundhound/Shazam app). Can you elaborate on the calendar domain?

hi, Well currently we support 4 actions within calendar, "CREATE_EVENT", "SEARCH_CALENDAR", "MODIFY_EVENT" and "DELETE_EVENT". There are a number of different entities including "dateRange, lengthOfTime, timeRange, date, time, meetingTopic, contactName, friendOrRelative, location, originalTime, originalDate, originalLocation, replacementTime, replacementDate" and a few others I'm sure I've missed. For reminder we sup…

Hi! Thanks for the reply! One more quick one. :) Are the "time" entities relative or absolute time or either?

Re: How would you use an accurate Natural Language Understanding (NLU) API?

#18

Post by ckrailo »

I wish there was something I could hook up to my electronic life (calendars, search engines, knowledge stores, bug tracking, etc) and send IMs to from all devices. Like Siri, but more useful and more connected. A general, all around AI instead of a glorified Google search with speech.

Example commands I wish I could do (some would require me hosting a server to communicate with my home, but I'm okay with this):

"Lock my doors." "I'm going home." (Notify people, set AC, bring up a map, etc.) "What's the weather tonight?" "Write 'happy birthday!' on my friends' Facebook walls each time it's their birthday." "Ask my girlfriend what's for dinner when she gets on Skype." ...and so on...

That said, I'm super excited about this and would love to see Maluuba's work accessible on all devices so I can just IM the service instead of using a phone when I'm at home.

Re: How would you use an accurate Natural Language Understanding (NLU) API?

#19

Post by jpantony »

fatbat wrote: post #17
pdat wrote: post #12

Earlier quoted context omitted.

hi, Well currently we support 4 actions within calendar, "CREATE_EVENT", "SEARCH_CALENDAR", "MODIFY_EVENT" and "DELETE_EVENT". There are a number of different entities including "dateRange, lengthOfTime, timeRange, date, time, meetingTopic, contactName, friendOrRelative, location, originalTime, originalDate, originalLocation, replacementTime, replacementDate" and a few others I'm sure I've missed. For reminder we sup…

Hi! Thanks for the reply! One more quick one. :) Are the "time" entities relative or absolute time or either?

Currently we support relative to the current time ("three hours from now") or absolute ("six pm"). We'd be happy to extend it however if we saw demand for extra functionality :) .

Re: How would you use an accurate Natural Language Understanding (NLU) API?

#20

Post by juharris »

hooande wrote: post #4

I would use a good natural language understanding api to do basic research, ideally monitoring many different feeds for topics of interest. It could also be a good way to monitor trends or competitors. I can't think of many uses cases for natural language as an interface to a traditional website. If there's something that's more convenient to access with text/speech, the user can just use set commands. On the topic o…

Actually, I've worked for a company that specializes in finding topics based on your interests. http://primal.com/
Post reply on HN