NLP for business process automation practical cases

Slides:



Advertisements
Similar presentations
Visit the ccScan Website Scan, Import, and Automatically File documents to the Cloud SCAN, IMPORT, AND AUTOMATICALLY FILE DOCUMENTS TO SALESFORCE ® Introduction.
Advertisements

General tax landscape.
WebEx Training Wednesday, January 22 nd Agenda Failed ID-Proofing Consumer not in DSS System Same Sex Marriages Couples Living Together.
Mind the Gap: Evaluating Internal Controls in Pharmaceutical Supply Chains across Sub-Saharan Africa AIDS 2012: July Julianna Kohler, Revathi Avasarala,
Deloitte Consulting LLP June 22-25, 2014 IIS 50 th Annual Seminar, London 2014 Big Data in Insurance International Insurance Society.
WebEx Training Wednesday, January 15 th Agenda Payment Locations Payment Extension Loss of Health Coverage on 01/31 Retroactive Special.
Leveraging CPQ Cloud for Channel Enablement Self Service Quoting for One and Two Tier Networks.
Pacific Cities Sustainability Initiative – Second Annual Forum Session 4: Public-Private Partnerships Case Studies Jim O’Gara, Director Deloitte Transactions.
Recommender systems Ram Akella February 23, 2011 Lecture 6b, i290 & 280I University of California at Berkeley Silicon Valley Center/SC.
Recommender systems Ram Akella November 26 th 2008.
Financial structure, management, and IFRS Reporting Creating value for growth Presenter: John Robinson Partner.
Lee Romero blog.leeromero.org November 2010 Enterprise taxonomy Six components of a vision.
WebEx Training Friday, January 31 st Agenda Clarification on Employer Coverage Disenrollment/Reimbursement In-House Patients providing Documentation.
Trade Across the Americas: Bolstering Security and Efficiency Supply Chain Risk Analytics May 2015.
Brand Resilience: Managing Risk and Recovery in a High Speed World Jonathan Copulsky Deloitte Consulting LLP Chief Executives’ Roundtable Series Lubbock,
Mike Wyatt, Director State Public Sector Cyber Risk Services
KNR- Studiedag 25 september 2013 Btw-checklist. © 2013 Deloitte The Netherlands KNR Studiedag Btw-checklist 1.
Provided by: Page 0 Training Module: Community Staples CDFI Deal Examples This training contains general information only and Deloitte is not, by means.
Indexed content Migrate content Create links Content for future indexing.
Georgia Gateway– Integrated Eligibility System (IES)
Alexey Kolosoff, Michael Bogatyrev 1 Tula State University Faculty of Cybernetics Laboratory of Information Systems.
WebEx Training Friday, February 7, Agenda Fast Alert - Medicaid Fast Alert - Complete Addresses & Names on Mailboxes Fast Alert - Dis-enrolling/Re-enrolling.
6.1 © 2010 by Prentice Hall 6 Chapter Foundations of Business Intelligence: Databases and Information Management.
Managing Data Resources. File Organization Terms and Concepts Bit: Smallest unit of data; binary digit (0,1) Byte: Group of bits that represents a single.
Credit Management Services
Kaggle Competition Prudential Life Insurance Assessment
© 2013 Deloitte Belgium DEF-Debate “Cyber Security – Risks and Opportunities for Europe’s Economy ” May 21 st 2014 Erik R. van Zuuren Director Deloitte.
MIS 374 Christine Lyman, Sr. Manager Jan 2015 Root Cause Analysis.
© 2013 Deloitte Global Services Limited Growing Markets for Social Impact September 16 th, 2014 Global Public SectorThinking people.
1Third Party Assurance Optimization and Control RationalizationCopyright © 2016 Deloitte Development LLC. All rights reserved. Third-Party Assurance (TPA)
How Do You Plan Inventory in an Omnichannel World? Integrated Merchandising, Planning, and Supply Chain Presentation and Panel Discussion Led by Jamie.
Scan, Import, and Automatically file documents to Box Introduction
Oracle Advanced Analytics
What business really needs
Getting started—the journey begins Transition Assistance Overview
4/19/ :02 AM © Microsoft Corporation. All rights reserved. MICROSOFT MAKES NO WARRANTIES, EXPRESS, IMPLIED OR STATUTORY, AS TO THE INFORMATION IN.
Resume Development: It IS all about you!
CS 388: Natural Language Processing: LSTM Recurrent Neural Networks
The Connected Job Search Online & Social Media Strategy
University of Stellenbosch Business School
Resume Development: It IS all about you!
Capital Project / Infrastructure Renewal – Making the Business Case
<Insert Picture Here>
Erasmus University Rotterdam
Will you R.I.S.E. to the challenge?
Insights driven Customer Experience
Confidence to Transform
Modernizing compliance: Moving from value protection to value creation
THE DEVELOPMENT SERVICE
Getting Started The job search journey begins
AGA 7th Annual Energy Market Regulation Conference Value Proposition for U.S. LNG Exports: Market Study October 2014.
Using LinkedIn for Your Job Search
MANAGING DATA RESOURCES
Explore. Discover. Focus.
DEF-Debate “Cyber Security – Risks and Opportunities for Europe’s Economy ” May 21st 2014 Erik R. van Zuuren Director Deloitte ERS BE Board Member EEMA.
Digital Innovation in Oil & Gas
Building sustainable HIV service delivery model at a local level in Ukraine Iaremenko Oleksii USAID HIV Reform in Action Project, Deloitte consulting LLP.
Reaching the first “90”: Decentralizing and strengthening Provider Initiated Testing services at primary health care facilities in Ukraine Mariya Makovetska,
Voice Activation for Wealth Management
Content Augmentation for Mixed-Mode News Broadcasts Mike Dowman
Maximizing the Impact of Learning & Development
Onboarding: Update Your Approach with Human-Centered Design
The Deloitte Industry Proficiency Program
Mobility Based Last Mile Banking Solution For
Confidence to Transform
Future of Charities and Tax – a Māori Perspective
Electronic health records Deploying knowledge at the Point of Care
Welcome! Knowledge Discovery and Data Mining
Attention for translation
Evolution of Competition: Beyond the Red Queen
Presentation transcript:

NLP for business process automation practical cases Deloitte Ukraine

Deloitte Ukraine Digital Solution Lab Deloitte Global 150 countries 286,000 people wordwide 150 years of history Ukrainian AI team Data Scientists / NLP Specialists Developers UI/UX designers Management team Deloitte named a leader by Gartner in Data and Analytics Service Providers, Worldwide

Common NPL use cases in automation Information extraction Semantic search Machine translation Data summarization Template fulfilling Dialogue support and navigation Documents classification and management

Deloitte use case 1: plenty web-sites analysis Business need Necessity to review, extract and summarize information from a large number of web-sites Issue Manual time-consuming process Subjective decisions Human-factor errors Challenges Multiple language content Non-standard web-sites structure Human-factor errors in data-labelling Tasks Text summarization Text generation Activity comparison

Text summarization and generation Ideas: Extract key words (wheat, sell) Combine them into the sentence (The company sells wheat)

Text summarization and generation p(product) p(activity) p(none)

Text summarization and generation LSTM p(product) p(activity) p(none)

Text summarization and generation p(product) p(activity) p(none) Database of urls and summaries used Summary from DB: Development of robotic solutions 2/3 non-stop words found!

Text summarization and generation Two approaches for text summarization Extractive summarization Abstractive summarization Select parts (typically sentence) of the original text to form a summary Easier Too restrictive Most past work is extractive Generate novel sentences using natural language generation techniques. More difficult More flexible and human Necessary for future progress

Text summarization and generation Final predicted Vocab Distribution 1-Pgen Pgen Attention Distribution Predicted Vocab Distribution Attention Encoder (BI-LSTM) Input-Sequence Decoder (RNN) Context vector

Text summarization and generation 43% of correct summaries More experiments are on the way Results: Text summarization and generation Joining two approaches: Our 100% <activity> Made </activity> in Italy <product> robotic solutions </product> ensure cutting edge performance that will last over time.

Activity comparison Idea: Compare with GloVe or something better

Selection of the mimimum distance for each criteria type Activity comparison Input criteria grain, wheat storage oil manufacturing machinery wholesale, trade ? Selection of the mimimum distance for each criteria type 0.51, 0.23 0.34 0.39 0.42 0.38 0.85, 0.31 ? Each with each word comparison using GloVe algorithm*. wheat (0.08,0.27) crop (0.24, 0.1) machinery (0.32, 0,6) distance ~ 0.236 Text from web-site We purchase, we accept for storage, we render services of completion and logistics of grain crops and sunflower.

Activity comparison ? Company 1: 0.31, 0.2, 0.45, 0.3 Random forest algorithm on 100 decision trees Simple voting process Probability of acceptance ….. Company 7999: 0.51, 0.1, 0.1, 0.36, X>0.3 Y<0.5 Z<0.8 Rejected Accepted W<0.8 True False Company 8000: 0.3, 0.22, 0.35, 0.67 0.31 0.23 ? 0.34 0.39 0.42 0.38

Probability of acceptance 92% recall 50% FPR Results: Activity comparison Random forest algorithm on 100 decision trees Probability of acceptance

Deloitte use case 2: documents analysis Business need Necessity to store large number of documents in the database with certain attributes that enable search Issue Manual time-consuming process Human-factor errors causing documents loose Challenges Multiple documents formats, including scanned pdfs Tough deadlines Poor labeling Tasks Document classification Attribute extraction

Attributes extraction Ideas: Annotate texts Use LSTM

Attributes extraction Receiving data from client Conversion to wildcard expressions tf-idf on limited vocabulary with logistic regression Models blending Key phrases: The client hereby agrees to use… Confidential work prepared for... client * agrees to… confidential work prepared * for… Documents and general information

95% F 0.5 Results: Attribute extraction

Possible solutions Advanced web-crawling Data capturing Customized search and information scraping via internet for marketing researches, reputation analysis, threat intel, KYC etc. Analysis, summarization and capturing of relevant information from web-sites, text documents, annual reports, 10K-reports etc. Templates pre-populating Data summarization & classification Filling templates with text or quantitative data, selected or generated using cognitive algorithm. Classification based on textual data in content of e-mails, documents, agreements etc.

Q& A

About Deloitte Deloitte refers to one or more of Deloitte Touche Tohmatsu Limited, a UK private company limited by guarantee (“DTTL”), its network of member firms, and their related entities. DTTL and each of its member firms are legally separate and independent entities. DTTL (also referred to as “Deloitte Global”) does not provide services to clients. Please see www.deloitte.com/about for a detailed description of DTTL and its member firms. Please see www.deloitte.com/us/about for a detailed description of the legal structure of Deloitte LLP and its subsidiaries. Certain services may not be available to attest clients under the rules and regulations of public accounting. Copyright © 2018 Deloitte Development LLC. All rights reserved. Member of Deloitte Touche Tohmatsu Limited