+ All Categories
Home > Technology > Deep learning for text analytics

Deep learning for text analytics

Date post: 14-Jan-2017
Category:
Upload: erik-tromp
View: 348 times
Download: 2 times
Share this document with a friend
39
(Technical) Big Data Analytics for non-technical end-users Erik Tromp – CEO UnderstandLing
Transcript
Page 1: Deep learning for text analytics

(Technical) Big Data Analytics

for non-technical end-users

Erik Tromp – CEO UnderstandLing

Page 2: Deep learning for text analytics

Contents• (Short) into• Rationale• Tuktu platform• Deep learning for computational linguistics• CEMistry – Customer Experience Monitoring on steroids

Page 3: Deep learning for text analytics

(Short) Intro

• Big data science experts• Specialisms• Computational Linguistics• Customer Experience Management

• Service: strategic advices all the way to operational implementation• Own platform: Tuktu• Soon: own product: CEMistry• Trainings/education on big data science

Page 4: Deep learning for text analytics

(Short) IntroQuantify every touchpoint of a customer with your company

4 major areas

• Text Analytics• Web Analytics• Mobile Analytics

• CRM/Backend Analytics

Page 5: Deep learning for text analytics

(Short) Intro• Erik Tromp• Age: 28• CEO UnderstandLing• Graduated on Sentiment Analysis in 2011• Multilingual Sentiment Analysis on Social Media

• Software engineer – Scala• Machine learning• Author of platform Tuktu

Page 6: Deep learning for text analytics

Contents• (Short) into• Rationale• Tuktu platform• Deep learning for computational linguistics• CEMistry – Customer Experience Monitoring on steroids

Page 7: Deep learning for text analytics

Rationale

Big data science allows to utilize opportunities

Page 8: Deep learning for text analytics

Rationale

Big data science allows to utilize opportunities

Big data science drives business

Page 9: Deep learning for text analytics

Rationale

Big data science allows to utilize opportunities

Big data science drives business

But is very much a technical revolution, with business implications

Page 10: Deep learning for text analytics

Rationale

Many companies want to utilize the opportunities big data science brings

Page 11: Deep learning for text analytics

Rationale

Many companies want to utilize the opportunities big data science brings

These companies do not have sufficient capabilities to do so

Page 12: Deep learning for text analytics

Rationale

Many companies want to utilize the opportunities big data science brings

These companies do not have sufficient capabilities to do so

Nor are there many suppliers that can do tech, analytics and know their business

Page 13: Deep learning for text analytics

Rationale

But these companies often do have their own (business) analysts

Page 14: Deep learning for text analytics

Rationale

IDEA

Make big data science accessible to non-technical users

Page 15: Deep learning for text analytics

Contents• (Short) into• Rationale• Tuktu platform• Deep learning for computational linguistics• CEMistry – Customer Experience Monitoring on steroids

Page 16: Deep learning for text analytics

Tuktu

http://www.tuktu.io

https://github.com/UnderstandLingBV/Tuktu

Page 17: Deep learning for text analytics

Tuktu – Early Days• Started off as a personal project to make life easier• Out of a collaboration with the Maastricht University• Idea: save time on coding/engineering, focus on logic and

functionalities

Page 18: Deep learning for text analytics

Tuktu – Early Days• Started off as a personal project to make life easier• Out of a collaboration with the Maastricht University• Idea: save time on coding/engineering, focus on logic and

functionalities

Instead of writing code over and over again, have it present and configure its building blocks

Page 19: Deep learning for text analytics

Tuktu – Early Days• Started off as a personal project to make life easier• Out of a collaboration with the Maastricht University• Idea: save time on coding/engineering, focus on logic and

functionalities

Instead of writing code over and over again, have it present and configure its building blocks

In a visual and straightforward way!

Page 20: Deep learning for text analytics

Tuktu – Now

Your one-stop shop for everything big data science

Page 21: Deep learning for text analytics

Tuktu – Now• Realtime and batch

processing• Synchronous and

asynchronous processing• REST API• Drag-and-drop modelling of

jobs• Distributed file system: TDFS• Key/value-sture: TuktuDB• Real-time visualization

• Web analytics support• Scheduling• No master/slave architecture• Local or distributed

computing• Machine learning• Deep learning• Cross-platform due to JVM• Easy installation: just unzip!

Page 22: Deep learning for text analytics

Tuktu

DEMO

Page 23: Deep learning for text analytics

Contents• (Short) into• Rationale• Tuktu platform• Deep learning for computational linguistics• CEMistry – Customer Experience Monitoring on steroids

Page 24: Deep learning for text analytics

Deep Learning for Computational Linguistics

IDEA

Learn language models generically

Page 25: Deep learning for text analytics

Deep Learning for Computational Linguistics

IDEA

Learn language models generically

Model every CL-problem on top on the generic model

Page 26: Deep learning for text analytics

Deep Learning for Computational Linguistics

This way, we can do almost any task on almost any language

Without too much/with less effort

Page 27: Deep learning for text analytics

Deep Learning for Computational Linguistics

How?

Page 28: Deep learning for text analytics

Deep Learning for Computational Linguistics

There are many linguistics resources available

Sadly; most is for EnglishIn particular: Annotated Treebanks for deep parsing

Page 29: Deep learning for text analytics

Deep Learning for Computational Linguistics

We can use this however

Page 30: Deep learning for text analytics

Deep Learning for Computational Linguistics1.Co-train word vectors for target language and English

Page 31: Deep learning for text analytics

Deep Learning for Computational Linguistics1.Co-train word vectors for target language and English2.Train parsing models on English language

Page 32: Deep learning for text analytics

Deep Learning for Computational Linguistics1.Co-train word vectors for target language and English2.Train parsing models on English language3.Co-finetune models on co-trained word vectors

Page 33: Deep learning for text analytics

Deep Learning for Computational Linguistics1.Co-train word vectors for target language and English2.Train parsing models on English language3.Co-finetune models on co-trained word vectors4.Pre-train (recursive) auto-encoder using parsing model for

target language

Page 34: Deep learning for text analytics

Deep Learning for Computational Linguistics1.Co-train word vectors for target language and English2.Train parsing models on English language3.Co-finetune models on co-trained word vectors4.Pre-train (recursive) auto-encoder using parsing model for

target language5.Use recursive auto-encoder for specific task in target

language• Topic detection, sentiment analysis, named entity recoginition,

authorship profiling

Page 35: Deep learning for text analytics

Deep Learning for Computational Linguistics

DEMO

Unsupervised parsing in Dutch

Page 36: Deep learning for text analytics

Contents• (Short) into• Rationale• Tuktu platform• Deep learning for computational linguistics• CEMistry – Customer Experience Monitoring on steroids

Page 37: Deep learning for text analytics

CEMistryTEXT ANALYTICS

MOBILE ANALYTICS

WEB ANALYTICS

BACKEND/CRM

Customer Profile

Tuktu.jsVisitor Customer

EventsPage views

Link

“SDK”Visitor Customer

EventsApp Triggers

Link

User CustomerCollectors

EventsCommunicati

on(NLP)

Link

(Database)ConnectorsCustomer

EventsTransactions

Link

Page 38: Deep learning for text analytics

Questions?

Page 39: Deep learning for text analytics

Erik TrompCEO UnderstandLing

[email protected]

http://www.understandling.comhttp://www.tuktu.io

http://www.linkedin.com/in/eriktromphttps://github.com/UnderstandLingBV/Tuktu

Talk to us on Gitter! https://gitter.im/UnderstandLingBV/Tuktu


Recommended