On Wed, Jun 27, 2012 at 3:50 PM, Jörn Kottmann <[email protected]> wrote:
> On 06/27/2012 03:34 PM, Nicolas Hernandez wrote:
>>
>> Since I like to use the maltparser [1], I need now to adapt the ftb to
>> a tag set called ftb+ as described by [2].
>> (only multi-word expressions which can be recognized by regular
>> expression are considered, some pos tags result in the concatenation
>> of the cat and subcat attributes...)
>>
>> I plan to do it by processing the MarkupAnnotations provided by the
>> Tika MarkupAnnotator [3].
>
>
> Do you plan to use the UIMA POS Tagger Trainer to produce a model for you?

Actually... I use the POS Tagger Trainer CLI because I use some tools
which detect and correct annotation errors but work on this format...

>
> We could add support for ftb+ tag sets to the code that produces training
> data
> out of the FTB.
>
> With the separator support in the training format that should work out fine
> in the end.
> The CLI tools also give you easy access to the build-in evaluation.
>
> Jörn



-- 
Dr. Nicolas Hernandez
Associate Professor (Maître de Conférences)
Université de Nantes - LINA CNRS UMR 6241
http://enicolashernandez.blogspot.com
http://www.univ-nantes.fr/hernandez-n
+33 (0)2 51 12 53 94
+33 (0)2 40 30 60 67

Reply via email to