On 11/14/2016 04:54 PM, Ben Goertzel wrote:
Nil,

Well, we do need to use the pattern miner for a couple projects pretty
soon... but that doesn't mean it has to be your job to fix it up...

It would be great though if you could write down a detailed list of
what you feel needs to be done to fix it up, so Hedra can give it a
shot (and maybe you can do some of the tricker bits?) ...

Sounds good. I'll look into it after tomorrow, merge my branch about it so far and try to sum up what remains to be done.

Nil


ben

On Mon, Nov 14, 2016 at 11:04 AM, Nil Geisweiller
<ngeis...@googlemail.com> wrote:
Hi,

the last time I reviewed the pattern miner I found that it was not ready for
general use, and estimated it would take me about 2 weeks to put it in
shape. I had started this branch for that
https://github.com/ngeiswei/opencog/commits/hack-pattern-miner

Anyway, I'll have a look at it within the next couple days, who knows, it
might not be much.

Hedra, could you create an issue on the opencog repo (basically re-pasting
your report and attaching your files there)? If you can reduce the KB and
dialogue size it's even better, maybe it could serve as a unit test.

Thanks,
Nil


On 11/14/2016 12:17 PM, Ben Goertzel wrote:

Thanks Hedra!

Nil -- I hate to distract you from the BC, but could you please take a
look at this sometime soon?  It seems Shu Jing is too busy to help
out, and I know you have played a bit with the Pattern Miner a few
months ago...

thx
ben

On Mon, Nov 14, 2016 at 7:27 AM, Hedra Seid <tanks...@gmail.com> wrote:

Hi Ben, Sorry for my late reply ...

Here attached are the scheme files I used to apply the OpenCog pattern
miner

STEPS I followed

1. Start opencog server with the config file  -c
../lib/opencog_patternminer.conf and relex server

2. Telnet to opencog server on port 17001

3. Access the scheme shell

4. (use-modules (opencog) (opencog nlp) (opencog nlp chatbot) (opencog
nlp
relex2logic))

I import those modules to use (nlp-parse) and let relex parse the
sentences
in the dialogue but it creates a VariableNode instance which the Pattern
miner considers as an error node type to have. To fix this I have to make
the atomspace free.

5. (clear)

6. (load-scm-from-file "test-dialogue.scm")
     (load-scm-from-file "back-ground.scm")

here the atomspace contains 9900 atoms

7. Exit the scheme shell and load the test pettern miner agent module

    loadmodule

/home/tanksha/opencog_ws/opencog/build/opencog/learning/PatternMiner/libTestPatternMinerAgent.so

8. From the opencog server I got this
Listening on port 17001
Debug: PatternMining start! Max gram = 4, mode = Depth_First
Start thread 0 from 0 to 7467
0% completed in Thread 0.

It stays like this for a long time ... the percent doesn’t increase.




On Fri, Nov 11, 2016 at 2:56 PM, Ben Goertzel <b...@goertzel.org> wrote:


Hedra,

I suggest you should upload to some repository the actual data that
you loaded into the Pattern Miner, and the exact script that you ran
to launch the pattern miner

That way Nil or Shujing can follow the exact steps that you did, and
see exactly how the bug was encountered.

Without a clear way to replicate the bug, it may be hard for them to
debug
it

I would like them to be able to exactly replicate what you did on
their machines...

thanks
ben

On Wed, Nov 9, 2016 at 9:36 AM, Hedra Seid <tanks...@gmail.com> wrote:

Okay, Ben

I checked the pattern miner with the provided example corpus file and
it
works fine. But the problem is it sometimes stop mining with unknown
reason
for me.

Here is what I tried

we are working on applying OpenCog pattern miner as a dialogue
assistance to
help the customer service in providing answers mining what has been
said
before (or mining from the knowledge base atomspace).

- We have dialogues parsed and loaded to the atomspace, and loading the
opencog pattern miner module, the cogserver results the  following

Error: instance link contains variables:
(VariableNode "$wF0EfmscF9F25N7BAoBtBNmDChd5Ep0Cd9q0") ;
[111651][111516]

- We write the Atomese representation of each dialogues (like the aiml
to
atomese representations) and load to the atomspace and start the
opencog
mining

here the pattern miner works and generates output files, but only the
2gram
results are extracted.

- adding some knowledge tried the same data but the pattern miner
stoped
mining reaching 40% ... calculating the surprisingness

On Wed, Nov 9, 2016 at 11:57 AM, Ben Goertzel <b...@goertzel.org> wrote:


Shujing, perhaps you can help with this?

Hedra, it would be good if you could give precise instructions for
replicating the problem.... that will make it easier for Shujing or
Nil
to
help...

Thanks
Ben

On Nov 9, 2016 08:07, "Hedra Seid" <tanks...@gmail.com> wrote:


Hello

I have been working with OpenCog pattern miner and it sometimes stack
and
stop mining at some point ... Have waited for Pattern miner result
more than
half an hour where the atomspace contains only 55 atoms and it stops
at 40%.
Any solutions?

--
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


https://groups.google.com/d/msgid/opencog/4ef5fae7-dd3f-410a-ae26-c9c4e8ee4f50%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.





--
With Regards!

Hedra Seid




--
Ben Goertzel, PhD
http://goertzel.org

“I tell my students, when you go to these meetings, see what direction
everyone is headed, so you can go in the opposite direction. Don’t
polish the brass on the bandwagon.” – V. S. Ramachandran





--
With Regards!

Hedra Seid









--
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 
https://groups.google.com/d/msgid/opencog/35fa3bed-ac7d-f18f-c92b-eed2a51af5f7%40gmail.com.
For more options, visit https://groups.google.com/d/optout.

Reply via email to