Search Mailing List Archives
[bioontology-support] tokenization function in Annotator?
Yannick Pouliot PhD
ypouliot at stanford.edu
Mon Oct 31 09:09:59 PDT 2011
From: Leyla Jael Garcia Castro [mailto:lj_garcia at yahoo.com]
Sent: Monday, October 31, 2011 3:07 AM
To: Yannick Pouliot PhD; support at bioontology.org
Subject: Re: [bioontology-support] tokenization function in Annotator?
There is a parameter wholeWordOnly I guess that could do the trick but you
could also have more annotations that you are looking for. Maybe give it a
try and see whether it gives you what you need.
Thx, I did notice that parameter but I believe it will likely introduce more
noise because it is not a selective truncation as is done with tokenization.
Q: I’m pretty sure that you’ve got a tokenization function in your parser (I
forget its name). If true, any chance of implementing it?
From: Yannick Pouliot PhD <ypouliot at stanford.edu>
To: support at bioontology.org
Sent: Sunday, October 30, 2011 10:58 PM
Subject: [bioontology-support] tokenization function in Annotator?
Howdy. The Annotator doesn’t recognize the term “heparinized” but does
recognize “heparin”. Q: Is there a function I can invoke to ask for
tokenization (i.e., removal of parts of terms associated with plurals,
adjectives, etc) when invoking the Annotator via REST?
Yannick Pouliot, PhD MBA
Division of Systems Medicine
Room X-147, MSOB
Stanford University School of Medicine
<mailto:ypouliot at stanford.edu> ypouliot at stanford.edu
bioontology-support mailing list
bioontology-support at lists.stanford.edu
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the bioontology-support