building smart natural language applications with data ninja services
TRANSCRIPT
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Building Smart Natural Language
Applications with Data Ninja Services T. Diep, S. Mukherjee*, H-T. Wu, P. Subasic, R. Sujithan, T. Sumiya, H. Yin
*Speaker DOCOMO Innovations, Inc., Palo Alto, CA
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Our mission is to enable companies of all sizes to build smart services
with content intelligence without having in-house advanced data
science and machine learning teams.
Smart Content Smart Sentiment
Smart Data Smart Learning
2
Introducing Data Ninja Services
https://dataninja.net
2011 DOCOMO Innovations, Inc. All Rights Reserved.
• Technologies
– Natural Language Processing (NLP) and Machine Learning
– Large-scale Data Analytics and Cloud Computing
• Applications
– Personal voice assistants
– Personalization and Recommendation systems
– Car navigation assistants
– Automated text categorization system
• Customers
– Large enterprises including NTT DOCOMO, Toyota, Pioneer, Nissan and
FueTrek
– Companies utilizing analytics to enhance service offerings and effectively
provide relevant, appropriate and targeted content
Data Ninja Services, Technologies,
and Customers
3
2011 DOCOMO Innovations, Inc. All Rights Reserved.
4
We are a Content Intelligence Platform
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Smart
Content
Smart
Data
Smart
Learning
Smart
Sentiment
REST API
public cloud or technology licensing API Endpoints
Smart Applications and Services
Unstructured
Data (text)
Structured Data
(Concepts, Categories and
Entities with Sentiments)
https://dataninja.net
5
Our Services are Accessed through APIs
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Smart Content service extracts meaningful categories,
concepts, entities and keywords from unstructured text for
broad use in analytics and data science applications.
Smart Content collects relevant data continually to add to its
knowledge-base.
Smart Content knowledge-base is extendable through its
configurable resource repository with custom user-defined
taxonomies and entity dictionaries.
Example Use Cases:
6
Overview of the Smart Content Service
Topic Detection and Tracking Concept-based Retrieval
Image Recommendation for Online Publishing Contextual Music Recommendation
Semantic Analysis of News Articles - demo
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Smart Content Demo
7
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Smart Sentiment assigns a positive, negative, neutral, or
“none” sentiment value to the content of a natural language
text document.
Sentiments are based on a weighted comparison of all words
denoting sentiment, such as “good”, “bad”, “lovely”,
“splendid”, etc.
Sentiments are assigned to each extracted entity (persons,
places, organizations, etc.).
8
Overview of the Smart Sentiment Service
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Example Use Cases:
•Brand reputation analysis/monitoring
•Product sentiment around release date
•Product reviews
9 -1
-0.8
-0.6
-0.4
-0.2
0
0.2
0.4
Sep
. 01
Sep
. 02
Sep
. 03
Sep
. 04
Sep
. 05
Sep
. 06
Sep
. 07
Sep
. 08
Sep
. 09
Sep
. 10
Sep
. 11
Sep
. 12
Sep
. 13
Sep
. 14
Sep
. 15
Sep
. 16
Sep
. 17
Sep
. 18
Sep
. 19
Sep
. 20
Sep
. 21
Sep
. 22
Sep
. 23
Sep
. 24
Sep
. 25
Sep
. 26
Sep
. 27
Sep
. 28
Sep
. 29
Sep
. 30
No
rmal
ize
d s
en
tim
en
t sc
ore
Date
Sentiment for “Volkswagen” in Sep. ‘15
The U.S. Environmental Protection Agency said Friday that Volkswagen intentionally
skirted clean air laws by using a piece of software that enabled about 500,000 of its
diesel cars to emit fewer smog-causing pollutants during testing than in real-world
driving conditions. The agency ordered VW to fix the cars at its own expense.
Smart Sentiment Use Cases
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Smart Data: Description and Use Cases
Access to our knowledge graph to complement the Smart Content service
allowing development of sophisticated data-science applications
• Concept & Category Contextual Search: Keyword suggestion &
expansion
• Related Concept Contextual Search
– Personalization by building user profiles based on browsing history
– Recommendation based on similar concepts
• Concept Popularity Lookup
– Smart search using concepts in addition to keywords to increase
accuracy
– Popularity-based disambiguation
– Trending visualization by finding trends of concepts and categories
for better decision making
• Smart Graph
– Generation of linguistics resources for domain-specific applications
• Induction Engine
– Discovery of hidden relationships among concepts to better reason
with text 10
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Smart Data Demo
11
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Application – “NewsBot Ninja Beta”
12
https://newsbot.dataninja.net
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Application – “NewsBot Ninja” (contd.)
13
https://newsbot.dataninja.net
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Application – “NewsBot Ninja” (contd.)
14
https://newsbot.dataninja.net
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Application – “NewsBot Ninja” (contd.)
15
https://newsbot.dataninja.net
2011 DOCOMO Innovations, Inc. All Rights Reserved.
Thank You!
16
https://dataninja.net