Have you done Natural Language Understanding?

[Bee]

It's looks complex to me.

Parse the text it's not enough because some words have different meaning depending on the context.

This involve Artificial Intelligence and usually is used expert systems with (or without) the capacity to learn.

Depending on the complexity you need to advise one application in the market for your project, I think this is your dilemma.

I'm on a project where they're trying to automate reading incoming emails and directing them to work queues.

They've decided they can scan the mails for certain words or strings. I said it's more difficult than that. You need to either parse the text to get some idea of sentence structure or use analytics that looks for millions of correlations involving frequency, other words near by etc etc.

So far it's failing badly. I've said it will never work but I could be wrong of course.

I just wondered whether you've seen this kind of thing and can pass on any pointers eg did you have limitations on mail format, mandatory title words etc. Did you succeed with string searching logic or did you have to use more sophisticated software?

[DimPrawn]

Dear Tim,

You previously suggested the best option is to cancel the policy, please be clear, this should not happen under any circumstances.

Regards,

Nancy

SQL going to route this to cancel policy or not?

[LondonManc]

like not to?
would not like to?
don't want to?
want to?
wouldn't want to?
won't?
will not be?
aren't planning to?
not thinking of?

etc.

Amazed you and SQL Server haven't knocked IBM Watson and Microsoft Cortana into a cocked hat.

Fell at the first hurdle dimmers.

Mine wasn't a difficult system to code for by comparison and the keywords used were business jargon. We're talking about 12 years ago here and it was a quick sideline project away from what I was mainly doing because I was the "SQL Server person"

[LondonManc]

SQL going to route this to cancel policy or not?

Wow, when did you lower yourself to level of tester?

[DimPrawn]

Wow, when did you lower yourself to level of tester?

Well, I'll leave you to it. NLP was solved by SQL Server 2000 over 15 years ago, I must have missed that bit in the help manual.

[LondonManc]

Well, I'll leave you to it. NLP was solved by SQL Server 2000 over 15 years ago, I must have missed that bit in the help manual.

All I was saying is that it can very much depend how much you want to achieve with it. Having worked in business intelligence (sometimes an oxymoron) for 20 years, I've had to do a fair bit of data mining. Generally there have been better requirements than "what would you do with this email without know what we'd want to do with it and/or what our company looks like".

[DimPrawn]

Dear Tim,

You know I said cancel the policy, well cancel everything I said about cancelling the policy. It makes no sense to cancel the policy now.

Regards,

Suity

Cancel the policy?

[Bee]

All I was saying is that it can very much depend how much you want to achieve with it. Having worked in business intelligence (sometimes an oxymoron) for 20 years, I've had to do a fair bit of data mining. Generally there have been better requirements than "what would you do with this email without know what we'd want to do with it and/or what our company looks like".

Business Intelligence is used for Datawarehouse and to create midleware events and alerts. I don't think it will work on this case, if yes will be limited.

[MrMarkyMark]

Business Intelligence is used for Datawarehouse and to create midleware events and alerts. I don't think it will work on this case, if yes will be limited.

[Einstein Jnr]

Have you done Natural Language Understanding?

Sounds like you have landed a never ending project - hope you are on a good rate, keep iterating, keep agile and keep billing - I keep hearing we are on the verge of a great break through in AI