[Corpora-List] spotting names of drugs

Phil Gooch philgooch
Tue Jan 8 23:55:40 CET 2013


UMLS is great, I use it all the time. But it's a kind of 'brute force' approach to identifying terms. My understanding of the original question was 'how do you identify a text string as potentially being drug name without a dictionary?'

The surrounding words can give useful cues as to whether the preceding or following one or two tokens might be a drug name, e.g. a dosage and/or administration route.

Phil

On Tue, Jan 8, 2013 at 5:34 PM, Ken Litkowski <ken at clres.com> wrote:


> The Unified Medical Language System<http://www.nlm.nih.gov/research/umls/index.html>has all the medical terminology one would ever want. It includes a
> component, RxNorm <http://www.nlm.nih.gov/research/umls/rxnorm/index.html>,
> that provides a pretty thorough starting point for drug names. Although
> these vast resources are essentially free in the U.S., there may be some
> restrictions outside the U.S.
>
> On 1/8/2013 10:45 AM, WHITELOCK, Pete wrote:
>
> I?m interested in the problem of spotting that a particular string
> that?s not in one?s dictionary is in fact the name of a drug. New drugs and
> their names are being created all the time and it?s pretty easy as a human
> to see a string in isolation and see ?yeh, that?s a drug name?. Anyone done
> anything similar to this? I vaguely recall some discussion of
> distinguishing boys? and girls? names (as an exercise in some textbook?).*
> ***
>
> ** **
>
> In addition, does anyone know where to get a list of drug names to use as
> the starting point. ****
>
> ** **
>
> Thanks for any help****
>
> ** **
>
> Pete Whitelock, PhD
> Principal Language Engineer, Technology****
>
> Academic Dictionaries
> Oxford University Press****
>
> ** **
>
> Oxford University Press (UK) Disclaimer
>
> This message is confidential. You should not copy it or disclose its
> contents to anyone. You may use and apply the information for the intended
> purpose only. OUP does not accept legal responsibility for the contents of
> this message. Any views or opinions presented are those of the author only
> and not of OUP. If this email has come to you in error, please delete it,
> along with any attachments. Please note that OUP may intercept incoming and
> outgoing email communications.
>
>
> _______________________________________________
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing listCorpora at uib.nohttp://mailman.uib.no/listinfo/corpora
>
>
> --
> Ken Litkowski TEL.: 301-482-0237
> CL Research EMAIL: ken at clres.com
> 9208 Gue Road Home Page: http://www.clres.com
> Damascus, MD 20872-1025 USA Blog: http://www.clres.com/blog
>
>
> _______________________________________________
> 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 -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 4993 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20130108/ccdf2873/attachment.txt>



More information about the Corpora mailing list