2011/02/22

[Link Grammar] Abridged summary of link-grammar@googlegroups.com - 7 Messages in 1 Topic

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

    Ben Goertzel <ben@goertzel.org> Feb 20 06:09PM -0500 ^
     
    Hi,
     
    If you just want to recognize and parse prepositional phrases, I
    believe there are some chunk parsers out there that will do what you
    want better than the link parser *currently* does
    more...
    "Andrew S. Townley" <ast@atownley.org> Feb 20 11:24PM ^
     
    Hi Linas,
     
    On 20 Feb 2011, at 10:41 PM, Linas Vepstas wrote:
     
    > attempted to do this, but I think that approach was fundamentally
    > flawed, and just didn't work. Anyway, the current parser is more...
    "Andrew S. Townley" <ast@atownley.org> Feb 20 11:34PM ^
     
    Hi Ben,
     
    On 20 Feb 2011, at 11:09 PM, Ben Goertzel wrote:
     
     
    > If you just want to recognize and parse prepositional phrases, I
    > believe there are some chunk parsers out there that will do what more...
    Ben Goertzel <ben@goertzel.org> Feb 20 06:44PM -0500 ^
     
    You may want to look at the chunk parsers integrated into OpenNLP...
     
     
    --
    Ben Goertzel, PhD
    CEO, Novamente LLC and Biomind LLC
    CTO, Genescient Corp
    Chairman, Humanity+
    Adjunct Professor of more...
    Linas Vepstas <linasvepstas@gmail.com> Feb 20 10:48PM -0600 ^
     
    > Hi Linas,
     
    > However, one of the things which occurred to me was that each parser was generally tightly coupled to the particular application, and everyone was writing their own parsers because more...
    "Andrew S. Townley" <ast@atownley.org> Feb 21 05:50PM ^
     
    On 20 Feb 2011, at 11:44 PM, Ben Goertzel wrote:
     
    > You may want to look at the chunk parsers integrated into OpenNLP...
     
    Know of any in C or C++? I've seen people do crazy things with gcj to more...
    "Andrew S. Townley" <ast@atownley.org> Feb 21 06:08PM ^
     
    Hi Linas,
     
    On 21 Feb 2011, at 4:48 AM, Linas Vepstas wrote:
     
    > markov-chain-inspired methods, are closer to what link-grammar
    > is, than the usual top-down BNF-style production-rule grammars 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.

No comments:

Post a Comment