freq with modal verbs in Spanish

[Brian Macwhinney]

Dear Macarena,
    The first question here is whether one can make a nice short list of all Spanish modals.  If they arise in V+V constructions, as in "debo salir", this is pretty easy, but when they involve “que” things get trickier linguistically, because I assume you don’t want to throw out all predicate complement constructions.  In English, this gets solved a bit by the historical process that is merging “to” with the model as in “hafta” for “have~to”.  There is a short list of these in the English MOR
    Based on this analysis, I could modify Spanish MOR.  Then I would also need to revise the training set to retrain the POST tagger.  I could possibly do this, once it is clear how to count what.

— Brian MacWhinney
Teresa Heinz Professor of Cognitive Psychology, 
Language Technologies and Modern Languages, CMU



> On Jul 30, 2021, at 8:00 AM, Macarena Quiroga <macarenasolquiroga at gmail.com> wrote:
> 
> Hi everyone,
> I want to run a freq analysis to count verb types and tokens, but I need to exclude those cases when the verb is a part of a periphrasis (for example: "debo salir" o "tengo que salir", which translates to "I must leave" or "I have to leave"). In those cases, I want to count the infinitive as a verb (salir), and don't count the modal verb (debo, tengo que). MOR doesn't seem to recognize modal verbs in Spanish and I wasn't able to create a v-mod.cut file by hand.
> A colleague suggested I use combo to find verb+verb or verb+preposition combinations, and then modify their respectives mor lines by hand, but I was wondering if you knew a way to automatize this, because it's a very big corpus.
> Thank you so much for your time.
> 
> --
> Macarena Sol Quiroga
> Lic. y Prof. en Enseñanza Media y Superior en Letras (UBA)
> Instituto de Educación (UNaHur)
> CIIPME - CONICET
> 
> 
> -- 
> 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/CANcNhDbMoYD9t89bXfb4MhTjwVcQZK4AwWmP-JraXy8eQO8tvQ%40mail.gmail.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/7287A20A-8A60-4EDB-8209-59696458B8D0%40andrew.cmu.edu.