During the grammar NLP discussion, someone asked about various parsers, well here is one that I am looking at now Download http://nlp.stanford.edu/software/lex-parser.shtml Stanfords parser, and a online version is here http://josie.stanford.edu:8080/parser/ James
> http://josie.stanford.edu:8080/parser/Fails the Turing test :-) "I ate pizza with {pepperoni|George|chopsticks}" all have the same parse. -- Matt Mahoney, [EMAIL PROTECTED]- Original Message From: James Ratcliff <[EMAIL PROTECTED]>To: agi@v2.listbox.comSent: Sunday, November 12, 2006 1:1
Yeha I noticed that right off.I was going to play and see if it would generate multiple parse trees for me, I know I saw one that would.If not I can handle that part on my end so long as it does a good representation of the POS grammar task.I was just happy this was easy to use, and had a simple sc
Several things:
1. Someone suggested these parsers to me:
Eugene Charniak's
http://www.cog.brown.edu/Research/nlp/resources.html
Dan Bikel's
http://www.cis.upenn.edu/~dbikel/software.html
Demos for both are at:
http://lfg-demo.computing.dcu.ie/lfgparser.html
It seems that they are similar in
From: YKY (Yan King Yin) <[EMAIL PROTECTED]>
To: agi@v2.listbox.com
Sent: Wednesday, November 15, 2006 8:59:45 AM
Subject: Re: [agi] One grammar parser URL
Several things:
1. Someone suggested these parsers to me:
Eugene Charniak's
http://www.cog.brown.edu/Research/nlp
3. If translating natural language to a structured representation is not
hard, then do it. People have been working on this for 50 years without
success. Doing logical inference is the easy part.
Actually, a more accurate statement would be "Doing individual logical
inference steps is the easy
Correct,
Using inferences only works in toy, or small well understood domains, as
inevitably when it goes 2+ steps away from direct knowledge it will be making
large assumptions and be wrong.
My thoughts have been on an AISim as well, but I am laying out the works for it
to be massivley avai
dnesday, November 15, 2006 6:50 PM
Subject: Re: [agi] One grammar parser URL
>> 3. If translating natural language to a structured representation is not
>> hard, then do it. People have been working on this for 50 years without
>> success. Doing logical inference is the ea
questions . . . .
- Original Message -
From: "Ben Goertzel" <[EMAIL PROTECTED]>
To:
Sent: Wednesday, November 15, 2006 6:50 PM
Subject: Re: [agi] One grammar parser URL
>> 3. If translating natural language to a structured representation is not
>> hard, then do it. People h
.listbox.com
Sent: Thursday, November 16, 2006 1:02 PM
Subject: Re: [agi] One grammar parser URL
whats your definition of diff of data and knowledge then?
Cyc uses a formal language based in logic to describe the things.
James
Mark Waser <[EMAIL PROTECTED]> wrote:
> However, i
On 11/16/06, James Ratcliff <[EMAIL PROTECTED]> wrote:
Correct,
Using inferences only works in toy, or small well understood domains, as
inevitably when it goes 2+ steps away from direct knowledge it will be
making large assumptions and be wrong.
My thoughts have been on an AISim as well, bu
agi@v2.listbox.com
Sent: Thursday, November 16, 2006 7:17:55 PM
Subject: Re: [agi] One grammar parser URL
On 11/16/06, James Ratcliff <[EMAIL PROTECTED]> wrote:
> Correct,
> Using inferences only works in toy, or small well understood domains, as
> inevitably w
On 11/17/06, Matt Mahoney <[EMAIL PROTECTED]> wrote:
Learning logic is similar to learning grammar. A statistical model can
classify words into syntactic categories by context, e.g. "the X is" tells
you that X is a noun, and that it can be used in novel contexts where other
nouns have been obse
nchronous network, some neurons would have slow response times and not
need to be updated every cycle. Of course this requires lots of
experimentation, and the experiments take a long time.
-- Matt Mahoney, [EMAIL PROTECTED]
----- Original Message
From: YKY (Yan King Yin) <[EMAIL P
"YKY (Yan King Yin)" <[EMAIL PROTECTED]> wrote:
On 11/16/06, James Ratcliff <[EMAIL PROTECTED]> wrote:
> Correct,
> Using inferences only works in toy, or small well understood domains, as
> inevitably when it goes 2+ steps away from direct knowledge it will be making
> large assumptions an
network, some neurons would have slow response times and not
need to be updated every cycle. Of course this requires lots of
experimentation, and the experiments take a long time.
-- Matt Mahoney, [EMAIL PROTECTED]
- Original Message
From: YKY (Yan King Yin)
To: agi@v2.list
.
- Original Message -
From: James Ratcliff
To: agi@v2.listbox.com
Sent: Friday, November 17, 2006 9:40 AM
Subject: Re: [agi] One grammar parser URL
Not quite gonna work that way unfortunatly. (I think)
The 10^9 figure you used was the compressed amount of data for a lifetime
slightly each run), but you could not use it to
decompress. I don't see that the requirement for deterministic computation
should be an obstacle to building a language model on a computer.
-- Matt Mahoney, [EMAIL PROTECTED]
- Original Message
From: James Ratcliff <[EMAIL PROT
ot;I ate pizza with {pepperoni|George|chopsticks}"
all have the same parse.
-- Matt Mahoney, [EMAIL PROTECTED]
- Original Message
From: James Ratcliff <[EMAIL PROTECTED]>
To: agi@v2.listbox.com
Sent: Sunday, November 12, 2006 1:11:32 PM
Subject: [agi] One grammar parser URL
Dur
19 matches
Mail list logo