Missatge de Francis Tyers <fty...@prompsit.com> del dia dt., 7 d’ag. 2018 a
les 0:13:
>
> I'd say that's feasible as it will have changed the topology of some
> transducers. Although in principle if the tagger is doing its job
> as expected, that shouldn't happen ... e.g. it should only happen if
> there is ambiguity left.
>
>
Is there any way to check if there is ambiguity left? Something like
printing the distinct probabilities of the different analysis?
I've been looking through the code, but I can't see any way of properly
debugging this. Ideas?
--
< Xavi Ivars >
< http://xavi.ivars.me >
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
_______________________________________________
Apertium-stuff mailing list
Apertium-stuff@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/apertium-stuff
