IPSyn coding

rose maier rosie.maier at gmail.com
Tue May 27 21:33:42 UTC 2014


Thank you, Melissa! That's very helpful.
The program Melissa mentions is available here (
http://www.hlt.utdallas.edu/~nisa/ipsyn.html), if anyone else is interested
in downloading it. The program (called "AC_IPSyn") accepts both CHAT and
SALT transcripts. In the published paper cited in Melissa's message, the
authors compare performance of AC-IPSyn to the program reported in Sagae,
Lavie and MacWhinney (2005) as well as the Computerized Profiling (CP)
package from Long, Fey and Channell (2004); both the average point
difference to a human coder and the point-to-point reliability for AC-IPSyn
are quite good. Running AC-IPSyn produces a "parsed" intermediate file for
each transcript, which I think I will be able to use to generate the
utterance-level measure of complexity I've been looking for.
Thanks again for your help!
Cheers,
Rose

Rose Maier
Doctoral Student
Department of Psychology
University of Oregon
Office: 1715 Franklin, room 214


On Tue, May 27, 2014 at 1:41 PM, Melissa Sherman <
melissa.c.sherman at gmail.com> wrote:

> A recent graduate at my University created an automatic IPSYN calculator
> as part of her dissertation:
>
> Hassanali, K. N., Liu, Y., Iglesias, A., Solorio, T., & Dollaghan, C.
> (2013). Automatic generation of the index of productive syntax for child
> language transcripts. *Behavior research methods*, 1-9.
>
> I did some work in that lab with CHAT formatted transcripts, so her
> program may take this type of transcript as input. I haven't read the
> article, so I can't comment on the accuracy of the IPSYN annotating.
>
> (As this is my first time posting, and I apologize in advance if this
> is inappropriate.)
>
> Melissa Sherman
> Doctoral Student
> Communication Sciences and Disorders
> The University of Texas at Dallas
>
>
> On Tue, May 27, 2014 at 2:16 PM, rose maier <rosie.maier at gmail.com> wrote:
>
>> Hello,
>> I'm interested in grammatical complexity of individual utterances, and
>> I'm hoping to use the IPSyn coding system as a first approximation. I know
>> there has been discussion of building a program to automatically calculate
>> IPSyn scores from CHAT transcripts. Is it possible at this point to use
>> information on the morpheme and syntax tiers to automatically determine
>> which of the 56 types of IPSyn constructions appear in each utterance?
>> Ideally, for each utterance, I'd like to know the highest scoring
>> construction from each category (NP, VP, QN, and SS), so I can calculate a
>> measure of the complexity of that utterance.
>> Thanks in advance for your help.
>> Regards,
>> Rose Maier
>> Doctoral Student
>> Department of Psychology
>> University of Oregon
>> Office: 1715 Franklin, room 214
>>
>> --
>> 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/CACjLnjCv70seK1kqNC2qJXUpYoM63qD_W1Mz9pV8%2B1KJrMa5rw%40mail.gmail.com<https://groups.google.com/d/msgid/chibolts/CACjLnjCv70seK1kqNC2qJXUpYoM63qD_W1Mz9pV8%2B1KJrMa5rw%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/CAJd4L%2Bj8rCWaA58MvTY3kAhVX0zck%3DZYDZspgVaCvLmimeK4UQ%40mail.gmail.com<https://groups.google.com/d/msgid/chibolts/CAJd4L%2Bj8rCWaA58MvTY3kAhVX0zck%3DZYDZspgVaCvLmimeK4UQ%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/CACjLnjAZHk-zMNxcQUpuH4sq%2BK3Nc%3D%2BxFtTSPL4p96bh7Tdrcg%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/20140527/64fad2fa/attachment.html>


More information about the Chibolts mailing list