conversational turns in CLAN?

Fri Dec 21 16:56:40 UTC 2018

Hello,

We looked into MLT and what it provided was the number of continuous
utterances by a single speaker, but not whether it was contingent on a
particular speaker. Apologies, my example did not include the case for
multiple speakers as in the following so we would want:

MLT would provide:
3 turns for MOT
1 turn for GMA
3 turns for CHI

Whereas what we are interested in is 5 turns if we count each response as
an initiation (specifying the child and MOT/GMA as adults):
MOT-CHI
CHI-GMA
MOT-CHI
CHI-MOT
MOT-CHI

Or 3 turns between an adult and child if we always take the utterances
before as an initiation and do not count each response as an initiation
(this is similar to how LENA calculates their automated conversational turn
measure):
MOT-CHI
MOT-CHI
MOT-CHI

*MOT: come here !
*CHI: xxx .
*GMA: come here and sit with me.
*GMA: let's get you up here.
*MOT: come here let's sing the A_B_C_s at s .
*MOT: ready ?
*MOT: a at l b at l c at l d at l .
*MOT: you don't want to sing ?
*CHI: no .
*MOT: are you sure ?
*CHI: no .

Basically, we are interested in trying to get an automated conversational
turn measure, that is similar to LENA's, but using transcriptions that we
have already vetted as being child-directed speech with our adult speakers
of interested already identified.

Janet

On Fri, Dec 21, 2018 at 8:40 AM Brian MacWhinney <macw at cmu.edu> wrote:

> Nan,
>
> Yes, you are right.  MLT will do this.  I tested on this small sample from
> Janet and it reports 3 turns for MOT and 3 for CHI.
>
> -- Brian
>
> On Dec 21, 2018, at 11:32 AM, Nan Bernstein Ratner <nratner at umd.edu>
> wrote:
>
> Wouldn't that be Mean Length of Turn? (MLT program?)
> N
>
> Nan Bernstein Ratner, F-, H-ASHA, F-AAAS, ABCLD
> Professor
> Hearing and Speech Sciences
> University of Maryland
> 0100 Lefrak Hall
> College Park, MD 20742
> nratner at umd.edu, 301-405-4217
>
> Co-director: FluencyBank (www.fluency.talkbank.org);
> http://languagefluency.umd.edu/
>
> President, International Fluency Association (IFA; http://theifa.org)
> Director, University of Maryland Autism Research Consortium (UMARC),
> www.autism.umd.edu
> Faculty, Language Science (languagescience.umd.edu; Neuroscience &
> Cognitive Neuroscience (NACS, nacs.umd.edu), Developmental Science Field
> Committee
>
> http://hesp.umd.edu/facultyprofile/bernstein%20ratner/nan
>
> My PubMed Bibliography
> <http://www.ncbi.nlm.nih.gov/sites/myncbi/1-UVaaDdREZ/bibliography/40436718/public/?sort=date&direction=ascending>
>
>
> On Thu, Dec 20, 2018 at 8:34 PM Janet Bang <jbang at stanford.edu> wrote:
>
>> Hello,
>>
>> We are trying to see if there's a way to automate a count of turns
>> between a child and an adult within a transcript. We saw that with CHIP, we
>> can get the number of responses to a child's utterance, but this value
>> counts multiple utterances as separate responses, rather than one turn.
>>
>> For example, for the following interaction we would count 5 turns:
>> MOT-CHI
>> CHI-MOT (MOT has 4 utterances, but count as 1 turn)
>> MOT (same MOT as one above)-CHI
>> CHI-MOT
>> MOT-CHI
>>
>> *MOT: come here !
>> *CHI: xxx .
>> *MOT: come here let's sing the A_B_C_s at s .
>> *MOT: ready ?
>> *MOT: a at l b at l c at l d at l .
>> *MOT: you don't want to sing ?
>> *CHI: no .
>> *MOT: are you sure ?
>> *CHI: no .
>>
>>
>>
>> Is there some way to combine MLT and CHIP to get a value that represents
>> turns as above? If that is too difficult, we could also go without the
>> responses serving as the initiation of the next turn, meaning that the this
>> would be 3 turns as in:
>> MOT-CHI
>> MOT(1 turn, 4 utterances)-CHI
>> MOT-CHI
>>
>> Apologies if I've missed this in another function,
>> 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 post to this group, send email to chibolts at googlegroups.com.
>> To view this discussion on the web visit
>> https://groups.google.com/d/msgid/chibolts/DM5PR02MB3275D80094B08E54CA78CCC5D7B80%40DM5PR02MB3275.namprd02.prod.outlook.com
>> <https://groups.google.com/d/msgid/chibolts/DM5PR02MB3275D80094B08E54CA78CCC5D7B80%40DM5PR02MB3275.namprd02.prod.outlook.com?utm_medium=email&utm_source=footer>
>> .
>> For more options, visit https://groups.google.com/d/optout.
>>
>
> --
> 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 post to this group, send email to chibolts at googlegroups.com.
> To view this discussion on the web visit
> https://groups.google.com/d/msgid/chibolts/CAAFocx5U0ENWSULgmRCyBFjmq8Brnmt-fJybUpbDg0Qv5E5P9w%40mail.gmail.com
> <https://groups.google.com/d/msgid/chibolts/CAAFocx5U0ENWSULgmRCyBFjmq8Brnmt-fJybUpbDg0Qv5E5P9w%40mail.gmail.com?utm_medium=email&utm_source=footer>
> .
> For more options, visit https://groups.google.com/d/optout.
>
>
> --
> 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 post to this group, send email to chibolts at googlegroups.com.
> To view this discussion on the web visit
> https://groups.google.com/d/msgid/chibolts/B353A61B-1E37-46D2-8458-F00DB6A7308C%40cmu.edu
> <https://groups.google.com/d/msgid/chibolts/B353A61B-1E37-46D2-8458-F00DB6A7308C%40cmu.edu?utm_medium=email&utm_source=footer>
> .
> For more options, visit https://groups.google.com/d/optout.
>

-- 
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 post to this group, send email to chibolts at googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/chibolts/CAC5V4hh4yWgA6C_wmBQUyT2bRNx8BX34sdoNqQX5WA5W6FtkzA%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/chibolts/attachments/20181221/f5515bea/attachment.htm>