uima-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Thilo Goetz <twgo...@gmx.de>
Subject Re: Which Steps can we done using UIMA in a text Mining Project.
Date Tue, 20 Jan 2009 13:23:10 GMT
Anuj Kumar Gupta wrote:
> I have check out UIMA sandbox components according to information Tagger
> component would work for POS tagging.
> but I am not able to execute and test that. how can i test POS tagging.?

Download the UIMA Annotator Addons binary package from
the UIMA download page.  The tagger is part of that
and comes with documentation.

> 
> Can I Checout ClearTK toolkit component ?

According to the instructions on their web page,
you can.  I haven't tried it myself, though.

> 
> Anuj
> 
> 
> On Tue, Jan 20, 2009 at 6:27 PM, Thilo Goetz <twgoetz@gmx.de> wrote:
> 
>> You can do all of these tasks in UIMA.  Sentence splitting
>> and tokenization, as well as POS tagging can be done with
>> the UIMA sandbox components.
>>
>> Entity detection is usually done with statistal methods, see
>> for example the ClearTK toolkit (http://code.google.com/p/cleartk/).
>>
>> I don't know of any off-the-shelf coreferencing solution, but
>> you could write one as a UIMA component.  There's a large
>> stack of literature on that topic, going all the way back to
>> the 70s at least ;-)
>>
>> I don't know what you mean by negation handling.
>>
>> HTH,
>>  Thilo
>>
>> Anuj Kumar Gupta wrote:
>>> Hi Thilo-
>>>
>>> I am working on a text Mining Project.
>>>
>>> the Project is like
>>>
>>> some Docs are as input or may be some Database as input.
>>>
>>> then detect sentence from the input. Detect Words(token) from the
>> sentence.
>>> Detect POS from it. Verb/noun phrase.
>>>
>>> Some entity detection. Co referencing (means suppose there is a sentence
>> in
>>> the doc like "Motorola is a good Mobile. It is a good Mp3 feature" so in
>> the
>>> 2nd sentence it would be replace with Motorola.)  this is called as co
>>> referenceing.
>>>
>>> So can we do co referencing in UIMA.
>>>
>>> Then Negation handling.
>>>
>>>
>>>
>>> So as all above task which tasks can we do in UIMA ?
>>>
>>>
>>>
>>> Any pointers would also be help full.
>>>
>>>
>>>
>>> Thanks.
>>>
>>> Anuj.
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>> On Tue, Jan 20, 2009 at 5:44 PM, Thilo Goetz <twgoetz@gmx.de> wrote:
>>>
>>>> Sorry, but it might help if you provided more
>>>> background.  I for one did not understand what
>>>> the question was.
>>>>
>>>> --Thilo
>>>>
>>>> Anuj Kumar Gupta wrote:
>>>>> Can any Body plz reply this Thread..
>>>>>
>>>>> -Anuj
>>>>>
>>>>> On Mon, Jan 19, 2009 at 7:18 PM, Anuj Kumar Gupta <virgoanuj@gmail.com
>>>>> wrote:
>>>>>
>>>>>> Hello Users-
>>>>>> In a text Mining Project. I need aprox some below steps.
>>>>>> so can you please let me know in these steps which steps can we done
>> in
>>>>>> UIMA independetly.
>>>>>>
>>>>>> Document
>>>>>>
>>>>>> |
>>>>>>
>>>>>> Sentence
>>>>>>
>>>>>>         |
>>>>>>
>>>>>> Words (tokenize)  (parsing)
>>>>>>
>>>>>>         |
>>>>>>
>>>>>> POS
>>>>>>
>>>>>>       |
>>>>>>
>>>>>> Verb Noun phrase
>>>>>>
>>>>>>                 |
>>>>>>
>>>>>> Entity Extraction
>>>>>>
>>>>>>                 |
>>>>>>
>>>>>> Co Reference
>>>>>>
>>>>>> |
>>>>>>
>>>>>> Nominal
>>>>>>
>>>>>>  |
>>>>>>
>>>>>> Pronominal
>>>>>>
>>>>>> |
>>>>>>
>>>>>> Ortal
>>>>>>
>>>>>> |
>>>>>>
>>>>>> Sentence Extraction
>>>>>>
>>>>>>                 |
>>>>>>
>>>>>> Negation Handling
>>>>>>
>>>>>> |
>>>>>> Writing to DB (MS SQL /ORACLE)
>>>>>>
>>>>>> Thanks-
>>>>>> Anuj
>>>>>>
> 

Mime
View raw message