This document discusses natural language processing and deep learning techniques for analyzing text and images. It describes how APIs can extract keywords, topics, themes and categories from documents and images. Examples are given of extracting descriptions from images using these techniques, as well as analyzing user interests based on Instagram photos. The document promotes two people from the company Beeva who work on natural language processing and deep learning projects.
Design and Development of a Provenance Capture Platform for Data Science
[API Days] Cooking with apis
1. Avenida
de
Burgos
16
D,
28036
Madrid
hablemos@beeva.com
www.beeva.com
BEE
PART
OF
THE
CHANGE
COOKING
WITH
APIS
CREATING
VALUE
WITH
IMAGES
AND
WORDS
NIEVES
ÁBALOS
ENRIQUE
OTERO
25. Link
to
slides
about
word
vectors
from
NIPS
2013
Deep
Learning
Workshop:
NNforText.pdf
Word
Vector
Space
Natural
Language
Processing
word2vec
(Google)
26. RegulariNes
in
Word
Vector
Space
Natural
Language
Processing
word2vec
(Google)
grammaNcal
gender:
masculine
&
feminine
Link
to
slides
about
word
vectors
from
NIPS
2013
Deep
Learning
Workshop:
NNforText.pdf
27. RegulariNes
in
Word
Vector
Space
Natural
Language
Processing
word2vec
(Google)
...
Vector
space
operaNons
deducNon
@
context:
country
&
capital
Link
to
slides
about
word
vectors
from
NIPS
2013
Deep
Learning
Workshop:
NNforText.pdf
33. (*)
there
are
two
men
who
appear
to
be
pracZcing
marZal
arts
(*)
a
cat
si[ng
inside
of
a
piece
of
luggage
(*)
real
examples
extracted
from
hp://deeplearning.cs.toronto.edu/i2t
...
unNl
NOW!