Really interesting indeed,

IBM Watson seems to have a Deep Learning component, too. I am curios about
an Apache cTAKES integration with Apache MXNet [1].

Alex

[1] - Apache MXNet: https://mxnet.incubator.apache.org/


On Thu, Oct 5, 2017 at 6:59 AM, Maite Meseure Hugues <
meseure.ma...@gmail.com> wrote:

> Hi Abilash Mathew,
>
> Pretty interesting. In fact I think that many systems use the same kind of
> approach but the success of each system is about the addition of the
> different components of the pipeline like the quality of dictionaries, the
> variety/diversity of data, the algorithm settings, etc.
>
> Here is another interesting article about IBM Watson:
> https://www.statnews.com/2017/09/05/watson-ibm-cancer/
>
> Best,
>
> Maite
>
> On Thu, Oct 5, 2017 at 6:54 AM, <abilash.mat...@cognizant.com> wrote:
>
> > Hi All,
> >
> > I have recently come  across below YouTube video and the documentation on
> > IBM Watson Medical Records Text Analytics Solution (MRTAS). Based on my
> > analysis, it follows the same approach as CTAKES ( uses same architecture
> > and dictionary lookups)  and also does the same kind of  data extraction.
> > This is just to check anyone noticed this similarity.
> >
> > https://www.youtube.com/watch?v=7c4kxYnuBNk
> >
> > http://www.medtechmedia.com/files/medtech_images/IBM_
> 110615_Final_PPT.pdf
> >
> >
> > Thanks,
> > Abilash Mathew
> > This e-mail and any files transmitted with it are for the sole use of the
> > intended recipient(s) and may contain confidential and privileged
> > information. If you are not the intended recipient(s), please reply to
> the
> > sender and destroy all copies of the original message. Any unauthorized
> > review, use, disclosure, dissemination, forwarding, printing or copying
> of
> > this email, and/or any action taken in reliance on the contents of this
> > e-mail is strictly prohibited and may be unlawful. Where permitted by
> > applicable law, this e-mail and other e-mail communications sent to and
> > from Cognizant e-mail addresses may be monitored.
> >
>

Reply via email to