Post on 16-Apr-2017
How to Prepare Unstructured Data for BI and Data
AnalyticsGeorge ROTH – CEO Recognos Inc.
Neil MITCHELL – Recognos Inc.
Webinar Starting Soon – Everybody is Placed on Mute
How to Prepare Unstructured Data for BI and Data
AnalyticsGeorge ROTH – CEO Recognos Inc.
Neil MITCHELL – Recognos Inc.
3
Housekeeping• All attendees are placed on Mute throughout the presentation• We will make available all the Webinar materials
– The slides will be emailed and the recording posted • Questions
– Please use the GoToWebinar “chat box” in the control panel to ask any questions
– These will be addressed at the end, as time allows, or written responses provided
• Polling– To improve these webinars we will ask for your feedback in the form of
polling questions– They are completely confidential– Multiple choice
4
AGENDA
A. Structured, Semi-Structured and Un-Structured ContentB. What is Data Preparation in Data ScienceC. The Swiss Army Knife of the Data ExtractionD.Processing of Unstructured Non-Classifiable content
and integrate all data (SDP - The Smart Data Platform)E. On boarding ETI or SDPF. About Recognos and Next StepsG.Q&A
5
A. Structured, Semi-Structured and Un-Structured Content
6
Data Assets Classification
7
The Problem – 3 data types
• 80% of the data in the enterprise is unstructured• Structured: in tables of a certain sort, object DBs, etc.• Semi Structured – XML Based• Unstructured
– Known content, classifiable – key words : Contracts, SEC Documents, Insurance Quote Document
– Unknown content – with known domain: Board Meetings– Unknown content with unknown domain: Panama Files, emails
(discovery suites)
8
Data Growth – 42.5% per year – New Data Analytics – N=ALL
9
B. What is Data Preparation in Data Science
10
Data Preparation (Gartner)
11
What is Data Preparation in Data Science
• In most of the presentations they will say that is a tedious task• There is no system that will do that• Not always we know what to prepare for the Data Science
applications • Example:
– NGO – Grant – needed to know the start dates, end dates, amount of money, name of project
– Needed to find the graph of the recipients to determine connections between recipients
– Prevent fraud for EU funds – or money laundering• Need to combine different data types (structured, semi-
structured and unstructured) and to provide for the next steps
12
C. The Swiss Army Knife for Unstructured Classifiable content
13
The Swiss Army Knife
14
Classifiable Unstructured Content
15
Content that is classifiable by Keywords
• In general legal content• Can determine the keywords• Examples:
– Contracts– SEC Documents– Different Legal Documents– Forms (IRS, INS, etc.)– Hospital Patient Info– Insurance Info– Etc.
16
Field Types with their Extraction MethodsType Field Type Definition Extraction Method Can be setup
by business people ?
Estimated Percentage in docs
Expected Accuracy
1Explicit Trainable These fields appear in the approximate same context, consistent across documents of the same type.
Human Assisted Machine Learning
Y 50%>75%
2Explicit Form Fields
These fields are always preceded by the same labels, same contexts, etc. Example are any IRS form, the 10K Header.
Predefined templates. Need to be setup. We are planning to create the UI for this, we don't have one. This was the method that was used for the 10Ks 6 fields.
Y 10%>95%
3Explicit List Fields These fields have the same values in all documents (with small variations) that are known from the beginning.
The user can define a library of "lists" , and can select a list at the document setup phase.
Y 10%>90%
4Implicit List Fields The expected values are predefined but are not present in the document. Need to be inferred from the text.
Semantic Scripts, needs a Semantic Infrastrucutre.
NO 5%>90%
5Semantic Fields These fields have values that are not consistent across documents and need semantic analysis.
Semantic Scripts, needs a Semantic Infrastrucutre.
NO 20%>90%
6Graphical Fields Presence
We encountered two fields. Signature Present, Seal Present.
Artificial Vision Neural Networks are used to detect those. The algorithms exist, need to be integrated.
YES 1%>95%
7Tables These are tables in a document. There are two table types, Manhatan Tables (no lines) and others.
Special Artificial Vision method to detect the table, regular expressioln to extract the fields after the table found.
YES 3%>95%
8Enhanced These fields are not in the document but can be found in some auxiliary data stores based on what is in the document.
These fields actualy are populated in the post extraction validation / augmentation process.
NO 1%>95%
100%
17
Swiss Army Knife for Data Extraction
18
ETI- Extract Transform Integrate Platform – Human in the loop Machine Learning
Document load•PDF files, containing text or images•Popular image file formats
Document digitization•OCR•Tokenization – identification of words, sentences, paragraphs within the document
Taxonomy definition•What are the target documents?
•What data do you want to extract?
Manual data extraction Example based machine learning
Manual data corrections if necessary – improves extraction
Automatic data extraction
Data publishing
Initial SetupMachine Learning
19
Demo for 10Khttp://playground.datafactory.recognos.ro/DevUI/#/demo
20
Examples: A Certificate of Incorporation – Insurance Contract
21
Need to define the taxonomy – list of fields
22
Data type classification
23
Key Words
24
Type of fields
25
Field Types
• Trainable: the filed is always in the document (explicit) , in the same context.
• Not Explicit – for example Has an Audit :Y/N – Has a Signature (Y/N) – Has a Signature (Y/N)
26
Derived Fields – not trainable – need to write a script
• Need to read the text and determine a Boolean Value
27
Need to interpret text and assign code – code fieldThe system cannot be trained for derived fields !!!
28
A semantic script for derived fields
29
Table Extraction – VERY DIFFICULT
30
Table Extraction
31
Table Processing
• One of the most difficult tasks• There are two table types: Manhattan Tables and Lined Tables• Need to detect where is the table, the “lines” (vertical and horizontal)• Extract the info• Use filters derived from visual perception research (the so called
Gabor filters) • The table line detection method was developed by Dr. Raul C.
Mureşan and Dr. Vasile Vlad Moca, founders of S.C. Neurodynamics S.R.L., for Recognos . Both Dr. Mureşan and Dr. Moca have an active neuroscience research career and are affiliated to the Romanian Institute for Science and Technology (RIST), studied at Max Planck Institute in Germany.
32
What is a Perceptron ? (Wikipedia)
• In machine learning, the perceptron is an algorithm for supervised learning of binary classifiers: functions that can decide whether an input (represented by a vector of numbers) belongs to one class or another. It is a type of linear classifier, i.e. a classification algorithm that makes its predictions based on a linear predictor function combining a set of weights with the feature vector. The algorithm allows for online learning, in that it processes elements in the training set one at a time.
33
34
Samples of the tables processing
35
How to measure the performance of the extraction process
• Not a simple problem • Multiple error types• Language• OCR quality – language dependent• OCR – open source, paid (Omni Page, Tesseract)
What will be reported
• True PositivesA true positive is a value that was extracted by ETI and was confirmed by the DA as correct.
• False PositivesFalse positives are values identified by ETI but corrected by the DA.
• True NegativesTrue negatives are values that were not found by ETI and the DA confirms that the value for that specific filed in the taxonomy is not present in the document. It can be either left empty by the analyst or it can be manually input without a reference in the document.
• False NegativesFalse negatives are values that ETI did not find in the document but the DA inputs the values and adds a reference in the document.
The system EPI – Extraction Performance Indicators
– Precision The precision of the data extraction will tell us how many of the identified values are correct from the total number of values extracted.
The correct values are the TP, while the total values are TP + FP (correct and incorrect).– Sensitivity
The sensitivity will tell us how many correct values we retrieved from the total values that could have been extracted.
The correct values are the TP, while the total values in the document are TP + FN. As defined above FN are the values that the system identified as missing but the DA found the in the document.
– Accuracy The Precision and Sensitivity deal only with the extracted values, and do not take into account the values that are really missing and the system correctly reports them as missing. Accuracy is the EPI that tells us how correct the system identifies ALL values, both existing and missing.
The correctly extracted values are both TP and TN while the total number is the sum of all four measurements.
38
Compliance Applications
• Provenance• Always keep link between the data points and the source• Can be deployed on the cloud
40
Data Teams• Need to create data teams• Data Analysts - responsible with the taxonomies – mapping• Validation rules • Manual intervention decreases in time
41
Poll
• Neil Poll
42
D. Processing of Unstructured Non-Classifiable content
SDP- Smart Data Platform)
43
Non-Classifiable Content
44
Content is Not Classifiable by keywords – not consistent
• Ontology based classification, extraction• What is an ontology ?• RDF• SPARQL• Used in Data Integration (Same As)• We can query Unstructured, Semi Structured and Structured
with the same query language
45
A few semantic terms….
• RDF• Ontology - OWL• Linked Data• Schema.org - Google• Data.gov• Data.uk
46
RDF
05/02/2023 47
Building Block RDF“There is a Person identified by http://www.w3.org/People/EM/contact#me, whose name is Eric Miller, whose email address is em@w3.org, and whose title is Dr.".
Triplets:(i) http://www.w3.org/People/EM/contact#me, http://www.w3.org/2000/10/swap/pim/contact#fullName, "Eric Miller"(ii) http://www.w3.org/People/EM/contact#me, http://www.w3.org/2000/10/swap/pim/contact#personalTitle, "Dr."(iii) http://www.w3.org/People/EM/contact#me, http://www.w3.org/1999/02/22-rdf-syntax-ns#type, http://www.w3.org/2000/10/swap/pim/contact#Person(iv) http://www.w3.org/People/EM/contact#me, http://www.w3.org/2000/10/swap/pim/contact#mailbox, em@w3.org
48
05/02/2023 49
Ontologies – OWL (The Panama Files)
From: https://www.linkedin.com/pulse/linked-leaks-powerful-hybrid-semantic-queries-panama-papers-kiryakov?trk=hp-feed-article-title-like
50
Ontology - http://protege.stanford.edu/
51
Online Course
52
Data.gov
53
Linked Data – www.linkeddata.org
55
Ontology Sample (OWL) – A Box – T Box
56
SPARQL – The Semantic Query Language (22 Million RDF triplets)
57
Sample analytics: occupation, countries mostly mentioned in Panama Files
58
Smart Data Platform – unifies all the data
59
The Smart Data Extraction and Integration Platform
60
Query Samples from Mark Logic (SPARQL – XQUERY)
61
Document Adviser
62
E. On boarding ETI or the SDP
63
Onboarding ETI or SDP
• Need to designate a “data Shepherd”• The data sources need to be analyzed by a business expert
(know what data is where) – bad practice example• Meta data governance is very important (taxonomies,
ontologies)• Gradually develop the ontology – not at once• Needs a champion in the enterprise, the beginning is hard• Work hand in hand with Data Analytics people• Start small and measure the ROI• Will have to find the “we don’t know what we don’t know”
facts….
64
F. About Recognos and Next Steps
65
What does Recognos have
• ETI – Human in the Loop Machine learning Extraction Platform• Deployment
– The Data - Subscription – Licensing – on premises – on boarding – training – support– On the Cloud – delivery on Q2
• Smart Data Platform – depends on every environment – analysis is needed – on boarding requires consulting
66
About Recognos
• Recognos Inc. - California based company – established in 1999• Has a partner company in New York – Recognos Financial • Recognos has a development company in Cluj Romania – 80
developers – established in 2000• From 2008 – Involved in Semantics• Main customers – Fisher Investments, DTCC - NY, Clarient - NY,
DST, Bank of Transylvania, OSF Budapest• About 50% of the revenue through licensing and recurring data
contracts
67
In the press
• http://www.mondovisione.com/media-and-resources/news/recognos-eti-creates-smarter-data-new-platform-extracts-transforms-and-integr/
• http://www.dataversity.net/data-extraction-system-unstructured-documents/•
http://www.information-management.com/news/big-data-analytics/recognos-financial-announces-release-of-ai-based-recognos-eti-10028249-1.html?utm_medium=email&ET=informationmgmt:e6092429:2042611a:&utm_source=newsletter&utm_campaign=daily-feb%2012%202016&st=email
• http://www.informationweek.com/big-data/big-data-analytics/7-ways-semantic-technologies-make-data-make-sense/d/d-id/1323580?image_number=8
• http://raconteur.net/technology/top-5-sectors-using-artificial-intelligence• http://www.fiercefinanceit.com/story/brain-over-brawn-semantic-technology-and-mac
hine-learning-take-new-role-man/2015-12-03• http://www.dataversity.net/semantic-technology-a-new-approach-to-financial-data/• http://www.recognos.ro/news-and-events/trends-in-ai-technology/#more-1211• http://www.paymentssource.com/news/paythink/artificial-intelligence-can-nab-money-
launderers-3023456-1.html• http://tabbforum.com/videos/artificial-intelligence-in-financial-services-2016-trends
68
Next Steps
• Proof of Concept (PoC)– We will sign an NDA as needed– We will import your documents– We will show you the power and ease of use of Recognos solution
• Pilot project– We will work with you on an ROI centric project
69
Contact
Neil Mitchellnmitchell@recognos.com408-838-9381
George Rothgroth@recognos.com