[Link Grammar] Abridged summary of link-grammar@googlegroups.com - 2 Messages in 1 Topic

  Today's Topic Summary

Group: http://groups.google.com/group/link-grammar/topics

• Building MT with LG [2 Updates]

 Topic: Building MT with LG

kiddo <wandi.lin13@gmail.com> Aug 17 06:08AM -0700 ^
 
HI all, I am a new comer.
 
I want to make a research about "building MT with LG", from English to
Indonesian (though someone had done it), but I can't find any article
or paper that give me some more...

Linas Vepstas <linasvepstas@gmail.com> Aug 17 12:08PM -0500 ^
 
Hi,
 
> But, I still don't get the specific technique to accomplish it.
 
> I hope there are some articles or papers which can give me more
> understanding about building MT with LG.
more...

--
You received this message because you are subscribed to the Google Groups "link-grammar" group.
To post to this group, send email to link-grammar@googlegroups.com.
To unsubscribe from this group, send email to link-grammar+unsubscribe@googlegroups.com.
For more options, visit this group at http://groups.google.com/group/link-grammar?hl=en.

[Link Grammar] Abridged summary of link-grammar@googlegroups.com - 6 Messages in 1 Topic

  Today's Topic Summary

Group: http://groups.google.com/group/link-grammar/topics

• [opencog-dev] hello [6 Updates]

 Topic: [opencog-dev] hello

Linas Vepstas <linasvepstas@gmail.com> Aug 16 01:12PM -0500 ^
 

> One project that has never been done, and is fairly good for a
> beginner I think, is to try to test how well RelEx works relative to
> other parsers...
[...]
> identical to RelEx's, but I more...

Ben Goertzel <ben@goertzel.org> Aug 16 11:18AM -0700 ^
 
Interesting, Linas...
 
So, my suggested project for the student interested in an NLP project,
was to use some scripts to transform a large corpus into dependency
form (tweaked to agree with more...

Linas Vepstas <linasvepstas@gmail.com> Aug 16 01:42PM -0500 ^
 
> was to use some scripts to transform a large corpus into dependency
> form (tweaked to agree with Stanford output format, say), and then
> test RelEx vs. Stanford on this large dependency more...

Ben Goertzel <ben@goertzel.org> Aug 16 11:47AM -0700 ^
 
Thanks Linas, that is a good suggestion
 
So for G Meera: perhaps Linas's suggestion would be a good place to
start. The task would be to modify RelEx to make use of the link
parser's new more...

Linas Vepstas <linasvepstas@gmail.com> Aug 16 02:13PM -0500 ^
 

> Following this, testing against a larger corpus as I suggested would
> be valuable..
 
Simply finding one that is compatbile or almost-compatible, and determining
just how different it is, more...

Ben Goertzel <ben@goertzel.org> Aug 16 12:24PM -0700 ^
 
Well what I found was a script for converting the Penn Treebank and
Brown Corpus to dependency-grammar format...
 
The task then becomes to try to tweak this script to give
Stanford-parser-style more...

--
You received this message because you are subscribed to the Google Groups "link-grammar" group.
To post to this group, send email to link-grammar@googlegroups.com.
To unsubscribe from this group, send email to link-grammar+unsubscribe@googlegroups.com.
For more options, visit this group at http://groups.google.com/group/link-grammar?hl=en.

[Link Grammar] Abridged summary of link-grammar@googlegroups.com - 3 Messages in 1 Topic

  Today's Topic Summary

Group: http://groups.google.com/group/link-grammar/topics

• SIGSEGV When Accessing Link Parser Through JNI [3 Updates]

 Topic: SIGSEGV When Accessing Link Parser Through JNI

Arya Tafvizi <arya.tafvizi@gmail.com> Aug 09 10:18AM -0400 ^
 
We asked this on stackoverflow.com as well (http://stackoverflow.com/questions/6997576/sigsegv-when-accessing-link-parser-through-jni
). Not sure which forum is best to address this question. more...

Linas Vepstas <linasvepstas@gmail.com> Aug 09 11:46AM -0500 ^
 
> compressed oops)
 
> Problematic frame:
 
> C [liblink-grammar.so.4+0xa180] linkage_get_num_words+0x0
 
Would you have the rest of the stack trace handy? Who called this?
Was it called by the more...

Arya Tafvizi <arya.tafvizi@gmail.com> Aug 09 01:03PM -0400 ^
 
I have attached one of the log files to this email. We checked and the
binaries are LGP 64bit. The get_words function is being called from
inside the LGP by more...

--
You received this message because you are subscribed to the Google Groups "link-grammar" group.
To post to this group, send email to link-grammar@googlegroups.com.
To unsubscribe from this group, send email to link-grammar+unsubscribe@googlegroups.com.
For more options, visit this group at http://groups.google.com/group/link-grammar?hl=en.

[Link Grammar] Abridged summary of link-grammar@googlegroups.com - 1 Message in 1 Topic

  Today's Topic Summary

Group: http://groups.google.com/group/link-grammar/topics

• RelEx to extract relations from papers [1 Update]

 Topic: RelEx to extract relations from papers

Rushdi Shams <rushdecoder@gmail.com> Jul 23 06:49PM -0400 ^
 
Hi, if I have the relations from the seven papers extracted by RelEx,
then I will compare this result with the one with my relation
extractor. I executed my relation extractor on these seven papers more...

--
You received this message because you are subscribed to the Google Groups "link-grammar" group.
To post to this group, send email to link-grammar@googlegroups.com.
To unsubscribe from this group, send email to link-grammar+unsubscribe@googlegroups.com.
For more options, visit this group at http://groups.google.com/group/link-grammar?hl=en.

[Link Grammar] Abridged summary of link-grammar@googlegroups.com - 2 Messages in 2 Topics

  Today's Topic Summary

Group: http://groups.google.com/group/link-grammar/topics

• RelEx to extract relations from papers [1 Update]
• Using the medical vocabulary with the Link Grammar Parser [1 Update]

 Topic: RelEx to extract relations from papers

Linas Vepstas <linasvepstas@gmail.com> Jul 23 01:50PM -0500 ^
 
> RelEx for comparing its result with another relation extractor. Can
> anybody help me by running RelEx over the papers and sending me the
> extracted relations?
 
What do you expect to do with more...

 Topic: Using the medical vocabulary with the Link Grammar Parser

Linas Vepstas <linasvepstas@gmail.com> Jul 22 09:04PM -0500 ^
 
Hi Peter,
 
Sorry for late reply, have been out on vacation.
 
> I've been spending some time cleaning up the EXTRA files in my 2003 extensions to LGP based on the UMLS Specialist lexicon. more...

--
You received this message because you are subscribed to the Google Groups "link-grammar" group.
To post to this group, send email to link-grammar@googlegroups.com.
To unsubscribe from this group, send email to link-grammar+unsubscribe@googlegroups.com.
For more options, visit this group at http://groups.google.com/group/link-grammar?hl=en.