<div dir="ltr">Hi Yunqing<div><br></div><div>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 <a href="http://openaccess.city.ac.uk/2112/">http://openaccess.city.ac.uk/2112/</a>).</div>
<div><br></div><div style>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.</div><div style><br></div><div style>
Cheers</div><div style><br></div><div style>Phil</div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Tue, Mar 19, 2013 at 9:57 AM, Yunqing Xia <span dir="ltr"><<a href="mailto:yqxia@tsinghua.edu.cn" target="_blank">yqxia@tsinghua.edu.cn</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="im HOEnZb">Dear Phil,<br>
<br>
You might be interested in UMLS:<br>
<br>
<a href="http://www.nlm.nih.gov/research/umls/" target="_blank">http://www.nlm.nih.gov/research/umls/</a><br>
<br>
which provides API to recognize medical terms in various forms<br>
including the mentioned medial mode and narrative mode. It is a very<br>
good system for medical term normalization. But the normalization<br>
process is probably string matching based and suffers low recall.<br>
Stemming and tokenization tools can be integrated to further improve<br>
performance.<br>
<br>
cheers,<br>
Yunqing<br>
<br>
<br>
<br>
</div><div class="HOEnZb"><div class="h5">On 19 March 2013 17:38, Phil Gooch <<a href="mailto:philgooch@gmail.com">philgooch@gmail.com</a>> wrote:<br>
> Thanks Carmela and Janne for the info. Janne: is your Norwegian corpus<br>
> available for research purposes? If so, could you provide details of how I<br>
> might obtain it?<br>
><br>
> Many thanks<br>
><br>
> Phil<br>
><br>
><br>
> On Tue, Mar 19, 2013 at 8:58 AM, Janne Bondi Johannessen<br>
> <<a href="mailto:jannebj@iln.uio.no">jannebj@iln.uio.no</a>> wrote:<br>
>><br>
>> Dear Phil.<br>
>> We have a Norwegian corpus of doctor-patient conversations that is 1.5<br>
>> million words and all the time increasing.<br>
>> Janne<br>
>><br>
>><br>
>> 2013/3/19 Phil Gooch <<a href="mailto:philgooch@gmail.com">philgooch@gmail.com</a>><br>
>>><br>
>>> Hi all<br>
>>><br>
>>> Does anyone know of any publicly available corpora (annotated or<br>
>>> otherwise) of patient and/or clinician narratives? For example, reflective<br>
>>> diaries, patient/therapist dialogues, psychiatric case histories?<br>
>>><br>
>>> I have plenty of discharge summaries and progress reports from physical<br>
>>> medicine, but these are written in a very 'medical model' and abbreviated<br>
>>> way. I'm looking more at the 'narrative medicine', person-centred angle.<br>
>>><br>
>>> Many thanks<br>
>>><br>
>>> Phil<br>
>>><br>
>>> _______________________________________________<br>
>>> UNSUBSCRIBE from this page: <a href="http://mailman.uib.no/options/corpora" target="_blank">http://mailman.uib.no/options/corpora</a><br>
>>> Corpora mailing list<br>
>>> <a href="mailto:Corpora@uib.no">Corpora@uib.no</a><br>
>>> <a href="http://mailman.uib.no/listinfo/corpora" target="_blank">http://mailman.uib.no/listinfo/corpora</a><br>
>>><br>
>><br>
>><br>
>><br>
>> --<br>
>> Janne Bondi Johannessen<br>
>> Professor<br>
>> The Text Laboratory, ILN,<br>
>> University of Oslo<br>
>> Tel: <a href="tel:%2B47%2022%2085%2068%2014" value="+4722856814">+47 22 85 68 14</a>, mob.: <a href="tel:%2B47%20928%20966%2034" value="+4792896634">+47 928 966 34</a><br>
><br>
><br>
><br>
> _______________________________________________<br>
> UNSUBSCRIBE from this page: <a href="http://mailman.uib.no/options/corpora" target="_blank">http://mailman.uib.no/options/corpora</a><br>
> Corpora mailing list<br>
> <a href="mailto:Corpora@uib.no">Corpora@uib.no</a><br>
> <a href="http://mailman.uib.no/listinfo/corpora" target="_blank">http://mailman.uib.no/listinfo/corpora</a><br>
><br>
</div></div></blockquote></div><br></div>