Skip to Content.
Sympa Menu

illinois-ml-nlp-users - Re: [Illinois-ml-nlp-users] query on FeX language

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] query on FeX language


Chronological Thread 
  • From: Sourajit Basak <sourajit.basak AT gmail.com>
  • To: "Gioja, Joshua Michael" <gioja AT ad.uiuc.edu>, Mark Sammons <mssammon AT illinois.edu>
  • Cc: "illinois-ml-nlp-users AT cs.uiuc.edu" <illinois-ml-nlp-users AT cs.uiuc.edu>
  • Subject: Re: [Illinois-ml-nlp-users] query on FeX language
  • Date: Wed, 23 Mar 2011 22:50:14 +0530
  • 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>

Josh,

Lets rewind a bit here and look at the output from the chunker.

$$java -Xmx512m edu.illinois.cs.cogcomp.lbj.chunk.ChunksAndPOSTags <plain_text_file>
POS Tagged and chunked:
[ADVP (WRB How) ] [VP (TO to) (VB call) ] [NP (DT an) (NNP XML-RPC) (NN method) ] [PP (IN from) ] [NP (NNP Java) (NNP code) ] (. ?)

Here everything within [] is a phrase. So my question is how to extract the phrase which contains the target word (or proper noun, in this case)

rgds,
Sourajit

On Wed, Mar 23, 2011 at 9:58 PM, Gioja, Joshua Michael <gioja AT ad.uiuc.edu> wrote:
Sourajit,

Mark sent a reply that what you ask may be possible with the phrase mode of Fex.  I know nothing about Fex's phrase mode, so you would have to ask him for help with that.

How do you define a phrase?  Does it just include the words before and after the targets, or is more parsing involved?
Your example is "How to call an XML-RPC method from Java code".
The targets are "XML-RPC" and "Java".
The phrases you said you want to be returned are "an XML-RPC method" and "Java code".  Should it be "from Java code" instead?

If the example is "How to call an XML-RPC Java method", what would be the phrases desired?


Josh

________________________________________
From: Sourajit Basak [sourajit.basak AT gmail.com]
Sent: Wednesday, March 23, 2011 11:08 AM
To: Gioja, Joshua Michael
Cc: illinois-ml-nlp-users AT cs.uiuc.edu
Subject: Re: [Illinois-ml-nlp-users] query on FeX language

Josh,
The targets will usually be proper nouns, in this case "Java" and "XML-RPC", which is manually set. I am interested in the phrase overlapping such nouns.

I am not that familiar with the source code, but can help if you can point out the file.

rgds,
Sourajit

On Wed, Mar 23, 2011 at 8:15 PM, Gioja, Joshua Michael <gioja AT ad.uiuc.edu<mailto:gioja AT ad.uiuc.edu>> wrote:
Sourajit,

In your example, is the target "from" and you're interested in the three-word phrases before and after that word, unless they're limited by the beginning of the sentence?

That feature rule probably doesn't exist in Fex but it's easy to add it, if you can recompile the code.
I will investigate.

Josh



________________________________________
From: Sourajit Basak [sourajit.basak AT gmail.com<mailto:sourajit.basak AT gmail.com>]
Sent: Wednesday, March 23, 2011 4:07 AM
To: Gioja, Joshua Michael
Cc: illinois-ml-nlp-users AT cs.uiuc.edu<mailto:illinois-ml-nlp-users AT cs.uiuc.edu>
Subject: Re: [Illinois-ml-nlp-users] query on FeX language

Hi Josh,
Consider this question - "How to call an XML-RPC method from Java code ?"

Here examples of non-overlapping phrases (limited to 3 words) are "an XML-RPC method", "Java code". Does FeX have any (special) rule for identifying a phrase ?

rgds,
Sourajit

On Tue, Mar 22, 2011 at 6:31 PM, Gioja, Joshua Michael <gioja AT ad.uiuc.edu<mailto:gioja AT ad.uiuc.edu><mailto:gioja AT ad.uiuc.edu<mailto:gioja AT ad.uiuc.edu>>> wrote:
Hi Sourajit,

For POS tags around the target, this is what I would use:

-1: t [-1,1]

What do you mean by "non overlapping phrases"?

Have you seen the attached file?  It is the best reference I could find for the FEX script file, but even after reading it I had to try a lot of different things before getting fex to work properly for me.

Josh

________________________________________
From: illinois-ml-nlp-users-bounces AT cs.uiuc.edu<mailto:illinois-ml-nlp-users-bounces AT cs.uiuc.edu><mailto:illinois-ml-nlp-users-bounces AT cs.uiuc.edu<mailto:illinois-ml-nlp-users-bounces AT cs.uiuc.edu>> [illinois-ml-nlp-users-bounces AT cs.uiuc.edu<mailto:illinois-ml-nlp-users-bounces AT cs.uiuc.edu><mailto:illinois-ml-nlp-users-bounces AT cs.uiuc.edu<mailto:illinois-ml-nlp-users-bounces AT cs.uiuc.edu>>] On Behalf Of Sourajit Basak [sourajit.basak AT gmail.com<mailto:sourajit.basak AT gmail.com><mailto:sourajit.basak AT gmail.com<mailto:sourajit.basak AT gmail.com>>]
Sent: Tuesday, March 22, 2011 4:25 AM
To: Sammons, Mark
Cc: illinois-ml-nlp-users AT cs.uiuc.edu<mailto:illinois-ml-nlp-users AT cs.uiuc.edu><mailto:illinois-ml-nlp-users AT cs.uiuc.edu<mailto:illinois-ml-nlp-users AT cs.uiuc.edu>>
Subject: Re: [Illinois-ml-nlp-users] query on FeX language

hi Mark,
I did go through these tutorials which helped my understanding of a feature space. But I think those do not contain illustrative examples of using FeX.

I am actually extracting feature space for question recognition. I am particularly interested in  -
2) What will be the feature rule in FeX for POS tags around the target ?
3) What will be the feature for non overlapping phrases around the target ?

If I am allowed, I am willing to enhance the tutorial after I am conversant with FeX.

rgds,
Sourajit

On Fri, Mar 18, 2011 at 9:28 AM, Mark Sammons <mssammon AT illinois.edu<mailto:mssammon AT illinois.edu><mailto:mssammon AT illinois.edu<mailto:mssammon AT illinois.edu>><mailto:mssammon AT illinois.edu<mailto:mssammon AT illinois.edu><mailto:mssammon AT illinois.edu<mailto:mssammon AT illinois.edu>>>> wrote:
Hi, Sourajit.

You might find the fex/snow tutorial helpful:

http://cogcomp.cs.illinois.edu/page/tutorial

-- what you are trying to do looks like the approach taken in the context-sensitive
spell checker.  You specify a set of target words, and only those words
generate examples.  However, instead of specifying the words in the script file,
you use the "-t" option and name the target words. Other applications are also
covered in the tutorial.

Regards,

Mark

---- Original message ----
>Date: Tue, 15 Mar 2011 13:58:28 +0530
>To: Mark Sammons <mssammon AT illinois.edu<mailto:mssammon AT illinois.edu><mailto:mssammon AT illinois.edu<mailto:mssammon AT illinois.edu>><mailto:mssammon AT illinois.edu<mailto:mssammon AT illinois.edu><mailto:mssammon AT illinois.edu<mailto:mssammon AT illinois.edu>>>>, illinois-ml-nlp-users AT cs.uiuc.edu<mailto:illinois-ml-nlp-users AT cs.uiuc.edu><mailto:illinois-ml-nlp-users AT cs.uiuc.edu<mailto:illinois-ml-nlp-users AT cs.uiuc.edu>><mailto:illinois-ml-nlp-users AT cs.uiuc.edu<mailto:illinois-ml-nlp-users AT cs.uiuc.edu><mailto:illinois-ml-nlp-users AT cs.uiuc.edu<mailto:illinois-ml-nlp-users AT cs.uiuc.edu>>>
>
>   hello,
>
>   I am trying to extract features as mentioned in the
>   following examples. The attached file contains the
>   sentence (question) and its POS annotated
>   representation. I have the following queries.
>
>   1)  Feature: One word each around the target word
>   Is this rule correct ? -1 loc: w(x=Java) [-1,1]; -1
>   loc: w(x=XML-RPC) [-1,1] I do not see the lexicon
>   and example populated; guess that the rule is not
>   fired. This fired "4 loc: w [-1, -1]" whereas this
>   "Java loc: w [-1, 1]" failed.
>
>   2) What will be the feature rule for POS tags around
>   the target ?
>
>   3) What will be the feature for non overlapping
>   phrases around the target ?
>
>   I am afraid I didn't fully comprehend the FeX
>   manual. A brief explanation for the above will be
>   extremely helpful.
>
>   rgds,
>   Sourajit
>________________
>Preprocessing steps:-
>#1. Example: How to call an XML-RPC method from Java code ?
>
>#2. POS tagger and chunker output
>$$java -Xmx512m edu.illinois.cs.cogcomp.lbj.chunk.ChunksAndPOSTags
<plain_text_file>
>POS Tagged and chunked: [ADVP (WRB How) ] [VP (TO to) (VB call) ] [NP (DT an)
(NNP XML-RPC) (NN method) ] [PP (IN from) ] [NP (NNP Java) (NNP code) ] (. ?)
>
>#3. Columnar output. Used as the actual corpus.
>$$  perl chunks_to_cols.pl<http://chunks_to_cols.pl><http://chunks_to_cols.pl><http://chunks_to_cols.pl> <pos_tagged_question>
>
>O       0       0       B-ADVP  WRB     How     x       0       0
>O       0       1       B-VP    TO      to      x       0       0
>O       0       2       I-VP    VB      call    x       0       0
>B-NP    0       3       B-NP    DT      an      x       0       0
>I-NP    0       4       I-NP    NNP     XML-RPC x       0       0
>O       0       5       B-PP    IN      from    x       0       0
>B-NP    0       6       B-NP    NNP     Java    x       0       0
>I-NP    0       7       I-NP    NNP     Code    x       0       0
>O       0       8       O       .       ?       x       0       0







Archive powered by MHonArc 2.6.16.

Top of Page