Skip to Content.
Sympa Menu

illinois-ml-nlp-users - Re: [Illinois-ml-nlp-users] Need a user manual

illinois-ml-nlp-users AT lists.cs.illinois.edu

Subject: Support for users of CCG software closed 7-27-20

List archive

Re: [Illinois-ml-nlp-users] Need a user manual


Chronological Thread 
  • From: Mark Sammons <mssammon AT illinois.edu>
  • To: "Geetali Dudhbhate" <gdudhbha AT asu.edu>
  • Cc: illinois-ml-nlp-users AT cs.uiuc.edu
  • Subject: Re: [Illinois-ml-nlp-users] Need a user manual
  • Date: Thu, 23 Jun 2011 15:32:11 -0500 (CDT)
  • List-archive: <http://lists.cs.uiuc.edu/pipermail/illinois-ml-nlp-users>
  • List-id: Support for users of CCG software <illinois-ml-nlp-users.cs.uiuc.edu>

Hi, Geetali.

There is nothing distributed as part of SRL to automatically generate
the more verbose labels -- at least, not in the current release. This
would be a problem because our web demo uses the PropBank frame
files, which are part of the copyrighted distribution from LDC.

The best I can suggest at present is, if you have the PropBank
corpus, to implement a postprocessing step that reads the SRL output,
and finds the relevant frame file for each labeled verb to look up the
argument labels.

Regards,

Mark

---- Original message ----
>Date: Thu, 23 Jun 2011 13:28:05 -0700
>From: Geetali Dudhbhate
><gdudhbha AT asu.edu>
>
>Subject: Re: [Illinois-ml-nlp-users] Need a user manual
>To: Mark Sammons
><mssammon AT illinois.edu>
>Cc:
>rizzolo AT gmail.com,
>
>illinois-ml-nlp-users AT cs.uiuc.edu
>
> Hi Mark,
>
> Thanks for the link!!
>
> Is there any way that I can make the output more
> verbose as mentioned in my initial query? Is there
> any instructional manual that maybe lists the
> options for various different types of output? Is
> there some input parameter which I have to provide
> to the code to make the output more verbose.
>
> Thanks & Regards,
> Geetali.
>
> On Thu, Jun 23, 2011 at 1:18 PM, Mark Sammons
>
> <mssammon AT illinois.edu>
> wrote:
>
> Hi, Geetali.
>
> The SRL was trained on the PropBank data; the
> labeling scheme has apparently changed slightly
> since the SRL training data was developed.
>
> Here is a starting point for information about
> PropBank:
>
> http://verbs.colorado.edu/~mpalmer/projects/ace.html
>
> Our demo uses the PropBank frame files, presenting
> the most common
> set of labels for each identified verb.
>
> Regards,
>
> Mark
> ---- Original message ----
> >Date: Thu, 23 Jun 2011 12:29:55 -0600
> >From: Geetali Dudhbhate
> <gdudhbha AT asu.edu>
> >Subject: [Illinois-ml-nlp-users] Need a user
> manual
> >To:
> rizzolo AT gmail.com
> >Cc:
> illinois-ml-nlp-users AT cs.uiuc.edu
> >
> >   Hi,
> >
> >   I have managed to install the SRL package
> now. On
> >   giving input as "At the end of the day ,
> 251.2
> >   million shares were traded ." , I get the
> output as
> >   :
> >
> >   (S1 (S (PP (IN At)
> >              (NP (NP (DT the)
> >                      (NN
> end))
> >                  (PP (IN of)
> >                      (NP (DT
> the)
> >                         
> (NN
> >   day)))))
> >          (, ,)
> >          (NP (QP (CD 251.2)
> >                  (CD million))
> >              (NNS shares))
> >          (VP (AUX were)
> >              (VP (VBN traded)))
> >          (. .)))
> >   At                   -   
> (AM-TMP*
> >   the                  -    *
> >   end                 -    *
> >   of                    -    *
> >   the                  -    *
> >   day                 -    *AM-TMP)
> >   ,                    
> -    *
> >   251.2              -    (A1*
> >   million             -    *
> >   shares            -    *A1)
> >   were              -    *
> >   traded          trade    (V*V)
> >   .                   
> -    *
> >
> >   If I run the same sentence on the SRL demo
> provided
> >   on
> >  
> http://cogcomp.cs.illinois.edu/demo/srl/results.php
> >   I also get some keywords like "temporal
> [AM-TMP]"
> >   and "thing being traded (away) [A1]". Is
> there any
> >   way in which I can make the output of the SRL
> >   package I have installed more verbose? Also
> is there
> >   some user manual to which I can refer, to
> better
> >   understand the meaning of the various tags
> used?
> >
> >   Thanks & Regards,
> >   Geetali Dudhbhate.
> >   MS-Computer Science.
> >   Arizona State University.
> >________________
> >_______________________________________________
> >illinois-ml-nlp-users mailing list
>
> >illinois-ml-nlp-users AT cs.uiuc.edu
> >http://lists.cs.uiuc.edu/mailman/listinfo/illinois-ml-nlp-users





Archive powered by MHonArc 2.6.16.

Top of Page