>> My idea is to give, streams of text ( i don't know what it is about) -- >
>> NLP pipeline --> stimulate atoms --> retrieve the atoms with high STI and
>> its related atoms and check whether any useful/important  info is obtained.
>> Regarding this, i would like to clarify and conform few things.
>>    1.  It is not possible to store atoms with high attention values in
>>    DB. There is no code for doing this at this time?.
>> No.

>>    1.   I can also never delete atoms once that are put into DB.?
>> Only because the code has not yet been written.  This is an unfinished
to-do item.

>>  I can give only the sentences which are grammatically correct into NLP
>> Pipeline?.
If they are not grammatically correct, then the parser will be very

> So when i give  incomplete sentences say human chats  like this
>> "MadMonkey's Jim Cramer next Weeeeeeeek investment htt brtt", it will be
>> parsed with low confidence value.
Yes.  You may as well have said "FruBlort's Jim Sxvghz next Fooooooood
investment sgdf etyhff"  -- its nonsense word-salad.   I have no clue what
it says. Who si Jim Cramer, wan why does MadMoneky posses him? What's that
got to do with investment? What's with the modem line-noise at the end? Are
those acronyms? or are they accidental junk?

The apostrophe-s allows the parser to recognize a possessive. The
capitalization allows it to guess proper names. The spelling-guesser might
be able to guess the correct spelling for "Weeeeeek", maybe.

> Apart from this, will it have impact on providing boost to atoms?
> No.


You received this message because you are subscribed to the Google Groups 
"opencog" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to opencog+unsubscr...@googlegroups.com.
To post to this group, send email to opencog@googlegroups.com.
Visit this group at https://groups.google.com/group/opencog.
To view this discussion on the web visit 
For more options, visit https://groups.google.com/d/optout.

Reply via email to