Bilingual MOR not running in CLANc

[Leonid Spektor]

Hi Rachel,

	I think the problem is with +s option. The +s"[- eng]" option tells MOR to run only on utterances that have "[- eng]" pre-code.

If your file is English-dominant, then to run MOR on only English utterances you need an option -s"[- spa]", if you want MOR to run only on Spanish utterances, then you need an option +s"[- spa]". In English-dominant data file there should not be any "[- eng]" pre-codes. If your data file has both "[- eng]" and "[- spa]" pre-codes, then +s"[- spa]" option will tell MOR to run only on Spanish utterances and +s"[- eng]" will tell MOR to run only on English utterances, but it is best not to mix those two pre-codes in the same data file.

If this still doesn't work, then please email one of your data files to me at spektor at cmu.edu <mailto:spektor at cmu.edu>.


Leonid.

> On Jul 1, 2022, at 18:28, Rachel Romeo <rachelromeo at gmail.com> wrote:
> 
> Hi all,
> 
> I am working with a bilingual English & Spanish corpora, and I'm using the newest version of CLANc (May 2022). When I run MOR on the second language, it runs fine with no errors, but the output files are not showing the %mor and %gra tiers for utterances that are fully in the L2 (e.g., lines with [- spa] for an English-dominant file). Additionally, individual words tagged with @s are getting tagged as expected, but it seems to not be happy with full utterances in the L2. 
> 
> For clarity's sake:
> I've got my mor grammar set to spa. Command:
> mor +s"[- eng]" EnglishDominantFile.cha
> 
> Will give me output like this:
> 
> *MOT:	[- spa] no pero no pegas +//.
> ######No dependent tiers given
> 
> *MOT:	mira at s this is a little piggie .
> %mor:	L2|mira pro:dem|this cop|be&3S det:art|a adj|little n|pig-DIM .
> %gra:	1|3|LINK 2|3|SUBJ 3|0|ROOT 4|6|DET 5|6|MOD 6|3|PRED 7|3|PUNCT
> ######seems to do fine with individual words
> 
> Am I doing something wrong? 
> 
> Thanks!
> Rachel 
> 
> -- 
> Rachel R. Romeo, PhD, CCC-SLP
> Assistant Professor 
> Department of Human Development and Quantitative Methodology
> Department of Hearing and Speech Sciences, by courtesy
> Program in Neuroscience and Cognitive Science
> University of Maryland College Park
> education.umd.edu/leadlab <https://education.umd.edu/leadlab>
> Phone: 301-405-2809
> Pronouns: she/her/hers
> 
> 
> -- 
> 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 <mailto:chibolts+unsubscribe at googlegroups.com>.
> To view this discussion on the web visit https://groups.google.com/d/msgid/chibolts/CALbyt0eCFDwSMT7hJzFDxRoTyZ6Ge2X2LuVK_rBOz5SdZDm%3Dsg%40mail.gmail.com <https://groups.google.com/d/msgid/chibolts/CALbyt0eCFDwSMT7hJzFDxRoTyZ6Ge2X2LuVK_rBOz5SdZDm%3Dsg%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/8E4369C4-22A1-4264-821A-0924496F6BA1%40andrew.cmu.edu.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/chibolts/attachments/20220701/043771a5/attachment-0001.htm>