[Corpora-List] Corpora of patient and clinician narratives

[Phil Gooch]

Hi Yunqing

Thanks, yes, UMLS is useful. I use MetaMap quite a bit. There's more
efficient ways of finding medical terms though - I use an approach based on
semantic decomposition of the underlying ontologies used by UMLS (see Chap
6 of my PhD thesis http://openaccess.city.ac.uk/2112/).

But, for my current research, I am looking for corpora of narratives. I'm
looking to extract narrative event chains, self-states and reciprocal role
relations.

Cheers

Phil


On Tue, Mar 19, 2013 at 9:57 AM, Yunqing Xia <yqxia at tsinghua.edu.cn> wrote:

> Dear Phil,
>
> You might be interested in UMLS:
>
> http://www.nlm.nih.gov/research/umls/
>
> which provides API to recognize medical terms in various forms
> including the mentioned medial mode and narrative mode. It is a very
> good system for medical term normalization. But the normalization
> process is probably string matching based and suffers low recall.
> Stemming and tokenization tools can be integrated to further improve
> performance.
>
> cheers,
> Yunqing
>
>
>
> On 19 March 2013 17:38, Phil Gooch <philgooch at gmail.com> wrote:
> > Thanks Carmela and Janne for the info. Janne: is your Norwegian corpus
> > available for research purposes? If so, could you provide details of how
> I
> > might obtain it?
> >
> > Many thanks
> >
> > Phil
> >
> >
> > On Tue, Mar 19, 2013 at 8:58 AM, Janne Bondi Johannessen
> > <jannebj at iln.uio.no> wrote:
> >>
> >> Dear Phil.
> >> We have a Norwegian corpus of doctor-patient conversations that is 1.5
> >> million words and all the time increasing.
> >> Janne
> >>
> >>
> >> 2013/3/19 Phil Gooch <philgooch at gmail.com>
> >>>
> >>> Hi all
> >>>
> >>> Does anyone know of any publicly available corpora (annotated or
> >>> otherwise) of patient and/or clinician narratives? For example,
> reflective
> >>> diaries, patient/therapist dialogues, psychiatric case histories?
> >>>
> >>> I have plenty of discharge summaries and progress reports from physical
> >>> medicine, but these are written in a very 'medical model' and
> abbreviated
> >>> way. I'm looking more at the 'narrative medicine', person-centred
> angle.
> >>>
> >>> Many thanks
> >>>
> >>> Phil
> >>>
> >>> _______________________________________________
> >>> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> >>> Corpora mailing list
> >>> Corpora at uib.no
> >>> http://mailman.uib.no/listinfo/corpora
> >>>
> >>
> >>
> >>
> >> --
> >> Janne Bondi Johannessen
> >> Professor
> >> The Text Laboratory, ILN,
> >> University of Oslo
> >> Tel: +47 22 85 68 14, mob.: +47 928 966 34
> >
> >
> >
> > _______________________________________________
> > UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> > Corpora mailing list
> > Corpora at uib.no
> > http://mailman.uib.no/listinfo/corpora
> >
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20130319/775d35f1/attachment.htm>
-------------- next part --------------
_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora