TEACHERS
GALLERY
PRICING
SIGN IN
TRY ZURU
GET STARTED
Loop
Audio
Interval:
5s
10s
15s
20s
60s
Play
1 of 18
Slide Notes
Download
Go Live
New! Free Haiku Deck for PowerPoint Add-In
Topic Extraction
Share
Copy
Download
0
25
Published on Mar 16, 2016
No Description
View Outline
MORE DECKS TO EXPLORE
PRESENTATION OUTLINE
1.
TOPICS
Photo by
bookfinch
2.
Current Process
Photo by
another.point.in.time
3.
Untitled Slide
Topics are hand made sets of keywords
Articles w/ keyword are assigned the topic
Photo by
Jacob Joaquin
4.
BENEFITS
Allows topics to be refined online
Human added topics have high fidelity
Photo by
Kaptain Kobold
5.
DRAWBACKS
Can't apply ML techniques to improve topics
Tied to keyword matching model
Low tagging accuracy
Photo by
michael.heiss
6.
The Options
Photo by
CarbonNYC [in SF!]
7.
Alchemy
8.
Alchemy
9.
BENEFITS
Handles all of our current classification tasks
Provides sentiment analysis
Photo by
Muffet
10.
DRAWBACKS
No full ontology available
Little control over how concepts / keywords are extracted
Photo by
Theen ...
11.
Watson
12.
BENEFITS
Very accurate search
Handles keyword expansion and other tagging
Improves without developer effort
Photo by
Martin LaBar
13.
DRAWBACKS
Hosted document storage
No control over search
Entity / topic extraction costs extra
Photo by
chrisotruro
14.
The Solution
Photo by
Trace Nietert
15.
Untitled Slide
Build it with Alchemy
Transition to Watson
Photo by
Charlie Stinchcomb
16.
To Prototyping!
Photo by
Sebastiaan ter Burg
17.
PLATFORM CHANGES
Add ontology information
Add topic extraction + creation to aggregator
Add support for category creation
Handle concepts
Photo by
Miguel Virkkunen Carvalho
18.
SOLR CHANGES
Use nested documents to support topic metadata
Use block join syntax to search
Restrict topic core to NC ontology
Photo by
rishibando
Andrew FigPope
×
Error!