Incorrect tagging in Spanish

[Brian Macwhinney]

Dear E.,
    As you see, statistical disambiguation is not 100% perfect.  In these cases, I can add a rule to ex.cut to simply block these two forms: tardes and cosas as verbs.  However, that means they will never be recognized.  They are pretty rare and this could be the best solution.  There is also an option to create prepost or postmortem rules for this, but that is overkill in these cases.  So, I will add these to ex.cut.  I am not seeing any problem with “dar”.

— Brian MacWhinney

> On Dec 14, 2022, at 6:09 AM, e jamieson <e.a.jamieson at outlook.com> wrote:
> 
> Hi all,
> 
> While using the Spanish MOR grammar on a number of transcripts, we have found in a number of cases that certain words are being incorrectly classified (not consistently). For example, 'cosas' is tagged as a form of the verb 'coser'; 'tardes' appears as a verb or adverb; 'dar' is tagged as preposition 'de'. The option to disambiguate is not given in these cases.
> 
> Does anyone have experience of this? Is there a fix that does not involve extensive hand correction?
> 
> Thanks and best wishes
> 
> E Jamieson
> 
> -- 
> You received this message because you are subscribed to the Google Groups "chibolts" group.
> To unsubscribe from this group and stop receiving emails from it, send an email to chibolts+unsubscribe at googlegroups.com.
> To view this discussion on the web visit https://groups.google.com/d/msgid/chibolts/43d1bf48-bb7f-4e41-a3e7-6987f3764da5n%40googlegroups.com.

-- 
You received this message because you are subscribed to the Google Groups "chibolts" group.
To unsubscribe from this group and stop receiving emails from it, send an email to chibolts+unsubscribe at googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/chibolts/8AD23499-498B-4F09-8344-DA0E3710B948%40cmu.edu.