mor tagging is as i-PL

Janet Bang janet.bang at gmail.com
Sun Jun 21 21:21:08 UTC 2020


Hi Brian,

Ah I see, I was just concerned that the part of speech tag was a ?, but we
are focusing on the lemma so I guess this doesn't matter in that case since
the morphemes are still being separated the way we want.

Thanks!
Janet

On Sun, Jun 21, 2020 at 1:59 PM Brian MacWhinney <macw at andrew.cmu.edu>
wrote:

> Dear Janet,
>     Most of the Spanish corpora have a %mor line in which the plural
> marker is coded as -PL, just as it is in English.  Spanish has very few
> irregular plurals, so &PL is uncommon.  Given the availability of tagging
> through MOR for Spanish, I would not recommend trying to pull off plurals
> from the main line.
>    As you note, we still rely on the -s tag for the plural of letters and
> proper nouns.  If you transcribe as s at l-s, you get n:let|s-PL which seems
> okay to me.  But I see that Mickey_Mouse-s comes out
> as n:prop|Mickey_Mouse–s which is not so great.  I can try to fix that, but
> this is a pretty rare case.
>
> --Brian
>
> On Jun 21, 2020, at 3:47 PM, Janet Bang <janet.bang at gmail.com> wrote:
>
> Hello,
>
> We had a couple of questions for how to capture plurals in Spanish
> transcription:
>
> 1. Plural of proper nouns
>
> In the example below, the plural form of the proper noun in English is
> noted with an "-s", but in Spanish this convention does not seem to work.
> Is there a way to capture the plural form on the main line in Spanish? I
> tried using an "&PL" on the main line which seems to work, but wasn't sure
> if there was a more preferred option?
>
> English only
> *FAT: you know those blue *Explorer-s* ?
> %mor: pro:per|you v|know pro:dem|those adj|blue *n:prop|Explorer-PL*
>
> Spanish only
> *MOT: hay *Mickey_Mouse-s* aquí.
> %mor: v|habe-3S&PRES&SPEC=have *?|Mickey_Mouse-s* adv|aquí=here
>
> Spanish with &PL
> *MOT: hay *Mickey_Mouse&PL* aquí.
> %mor: v|habe-3S&PRES&SPEC=have *n:prop|Mickey_Mouse&PL* adv|aquí=here
>
>
> 2. Plural letters in Spanish (also with two different special lexical
> forms):
>
> In the example below, the "s at s@l-s" is meant to denote that the mother
> pronounces the letter "s" in English (@s), but we also wanted to tag this
> as a letter (@l), and she uses the plural form. When we run MOR it doesn't
> seem to recognize how to break up this form, whereas in English we are able
> to get the breakdown to a plural letter. Is there a way we can tag the "s"
> as 1) second language 2) letter 3) plural?
>
> English only
> *MOT: [- eng] look here we have the *s at l-s* .
> %mor: cop|look adv|here pro:sub|we v|have det:art|the *n:let|s-PL*
>
> Spanish/English
> *MOT: mija, aquí las tienes las *s at s@l-s*.
> %mor: co:voc|mija cm|cm adv|aquí=here pro:obj|la&f-PL=she
> v|tene-2S&PRES=have det:art|el&f-PL=the *?|s at s-s *
>
> Thank you!
> Janet
>
>
>
>
> On Wed, Jul 31, 2019 at 7:16 AM Brian MacWhinney <macw at andrew.cmu.edu>
> wrote:
>
>> Dear Janet,
>>
>>     For MOR to work properly on this, you need to transcribe this as
>> i at l-s.  It is ugly, but for the plurals of letters, this is the way it
>> must be done.
>>
>> -- Brian MacWhinney, Teresa Heinz Professor of Cognitive Psychology,
>> Computational Linguistics, and Modern Languages, CMU
>>
>> > On Jul 30, 2019, at 9:04 PM, Janet Bang <jbang at stanford.edu> wrote:
>> >
>> > Hello,
>> >
>> > I apologize, I don't believe there is anything wrong with the mor
>> library. We had included the letter "i" as a noun in order to capture the
>> following sentence:
>> >
>> > Here "i" is referring to the letter.
>> > MOT: she know's all her i's
>> >
>> > In this example, "i" was coming up as an unknown word, and we were not
>> able to do i at l's. Is there a way for us to transcribe this line to
>> capture this as a plural of the letter i? Or some way to include this
>> letter to our internal library to capture this as a different type?
>> >
>> > Thank you,
>> > Janet
>> >
>> >
>> > On Tue, Jul 30, 2019 at 4:32 PM Janet Y Bang <jbang at stanford.edu>
>> wrote:
>> > Hello,
>> >
>> > We are running the following code to get word types:
>> > freq +sm;*,o% @
>> >
>> > We noticed that for some instance of "is", that mor is treating it as
>> is-PL:
>> > *MOT: I don't think I know what a pegasus is .
>> > %mor: pro:sub|I mod|do~neg|not v|think pro:sub|I v|know pro:int|what
>> det:art|a n|pegasus n|i-PL .
>> >
>> >
>> > Do you have suggestions for how we might be able to fix this
>> automatically?
>> >
>> > Thank you,
>> > Janet
>> >
>> >
>> >
>> > --
>> > Janet Y. Bang, Ph.D.
>> > Postdoctoral Fellow
>> > Department of Psychology
>> > Stanford University
>> >
>> > jbang at stanford.edu
>> >
>> >
>> >
>> >
>> >
>> > --
>> > 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/DM5PR02MB32759CF15B15B27B87E5D5C3D7DC0%40DM5PR02MB3275.namprd02.prod.outlook.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/CAC5V4hiKC3fMRpFjEGMrASH0wVJ4iLyCaZs_Yz-zrOh5WDF5Mg%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/1CB61E64-4999-432A-A72D-D90FEB77C590%40andrew.cmu.edu
>> .
>>
>
> --
> 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/CAC5V4hg0z4ZfP7UZT3zSOrZrZKEfSHVpxuM_uNtKYCXV9J738w%40mail.gmail.com
> <https://groups.google.com/d/msgid/chibolts/CAC5V4hg0z4ZfP7UZT3zSOrZrZKEfSHVpxuM_uNtKYCXV9J738w%40mail.gmail.com?utm_medium=email&utm_source=footer>
> .
>
>
>

-- 
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/CAC5V4hhnJznA98Tgacu-mqeeJAoBZoe_PNWuzrPwWzyHBNPTxQ%40mail.gmail.com.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/chibolts/attachments/20200621/1f4cfef5/attachment.htm>


More information about the Chibolts mailing list