Thank for your advices, I am a novice in computer linguistics, I have
to learn more about HFST, but now I am looking for a framework like
Two-Level Morphology, although is a "old" paradigm (80' 90'), was
the first general model in the history of computational linguistics
for the analysis and generation of morphologically complex languages.
For the moment I want to try PC-Kimmo, this is a software for the
implementation of the two-level model, the output when you parse a
english word, e.g. relationships, is:
PC-KIMMO TWO-LEVEL PROCESSOR
Version 2.1.13 (October 25, 2002), Copyright 2002 SIL
Compiled Sep 19 2011 15:32:52
with PC-PATR functions version 1.3.12 (December 7, 2005)
Type ? for help
PC-KIMMO>take englex
PC-KIMMO>recognize relationships
re`late+ion+ship+s re`late+NR23e+NR9+PL
1:
Word
______|_______
Stem INFL
_____|______ +s
Stem SUFFIX +PL
___|____ +ship
Stem SUFFIX +NR9
| +ion
ROOT +NR23e
re`late
re`late
Word:
[ cat: Word
head: [ agr: [ 3sg: - ]
number:PL
pos: N ]
root: re`late
root_pos:V
clitic:-
drvstem:- ]
1 parse found
PC-KIMMO>
It is amazing, I dont know if HFST can do a tokenization and parsing
like that?
sofia
2011/9/18 Trond Trosterud <[email protected]>:
> lttoolbox is good for segmental morphology, and better the more agglutinative
> it is.
>
> HFST and related frameworks are better when you have autosegmental
> morphology: You may make one segmental transducer, and a separate transducer
> for the autosegmental morphology, and for complex morphological processes. I
> did not look into bribri, but from what i know about American langguages they
> are quite complex, and you should really look into HFST.
>
> Also, if you want to have your system master the Bribri tones, then HFST etc.
> is a good choice.
>
> Trond.
> ------------------------------------------------------------------------------
> BlackBerry® DevCon Americas, Oct. 18-20, San Francisco, CA
> http://p.sf.net/sfu/rim-devcon-copy2
> _______________________________________________
> Apertium-stuff mailing list
> [email protected]
> https://lists.sourceforge.net/lists/listinfo/apertium-stuff
>
------------------------------------------------------------------------------
All the data continuously generated in your IT infrastructure contains a
definitive record of customers, application performance, security
threats, fraudulent activity and more. Splunk takes this data and makes
sense of it. Business sense. IT sense. Common sense.
http://p.sf.net/sfu/splunk-d2dcopy1
_______________________________________________
Apertium-stuff mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/apertium-stuff
