Washington DC, November 2011George Roth, Adonis Damianwww.recognos.com
 A document management system (DMS) is a computer system (or  set of computer programs) used to track and store electroni...
CLASSICAL           NEW   Metadata           Compliance   Integration        Accessibility   Capture            Inte...
   Volume   Labor extensive   The “research project” – 40% – 60% data    gathering   Metadata independent of content ...
   NLP Natural Language Processing –    understand the meaning of documents    (statistic, machine learning, hybrid, grap...
   Inside – Controlled Environment - TRUST   Inside – Security issues   Same techniques as outside the enterprise   In...
New features will become commodity in 2-3 years   Compliance   Data Extraction, Comparison, Change    Analysis   Intera...
   Microsoft: Powerset (Bing), Fast Search, Jinni   Google: Freebase, Needlebase   Apple: SIRI   Etc…November 2011
 Embedded Compliance RulesNovember 2011
 Example there is a rule: – email –Rule 0134C: “Not allowed to mention a percentage as a  profit promise investing with t...
   MFIP data extraction   Link to the original documentNovember 2011
 Data Extraction, Comparison,    Change AnalysisNovember 2011
November 2011
November 2011
   Create Alarm when Trading Policy Changes   Create Alarm when Commissions Change    (fields)   Create Alarms when mem...
 InteractivityNovember 2011
November 2011
 AugmentationNovember 2011
November 2011
 Automated TranslationNovember 2011
   Google Translate     Great for simple translation – emails, non        technical documents   Language Weaver     Sp...
 Sentiment AnalysisNovember 2011
   Media Sentry   Open Amplify, Expert Systems, Lymbix   NLP and machine learningNovember 2011
November 2011
 SearchNovember 2011
November 2011
November 2011
November 2011
November 2011
November 2011
November 2011
 Complex App SamplesNovember 2011
November 2011
WWW                 Google        Meltwaters                                            Forums /                          ...
   Amdocs AIDA (AMDOCS Intelligent Decision Automation)November 2011
November 2011
Display Linked Data   Ask a question –   Entity Lookup                       semantic searchNovember 2011
November 2011
November 2011
November 2011
November 2011
November 2011
November 2011
   Interactive - Exists   Search – Semantic Search, Q&A   Semantic Tagging – Summarization   LOD with domains   Linke...
The following technologies were used:- iQser – GIN- Clark & Parsia – Spanner, StarDog- Expert System – NLP- GATE- Smart Lo...
George RothPresident and CEO Recognos Inc.San Franciscowww.recognos.comgroth@recognos.comDrew WarrenCEO Recognos Financial...
Upcoming SlideShare
Loading in …5
×

Semantic Technology in Document Management

1,477
-1

Published on

This is the vision of Recognos about the future of Semantic Technology in Document Management. The presentation was created for the SemTech Conference in November, 2011 in Washington DC.

Published in: Technology, Business
0 Comments
3 Likes
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total Views
1,477
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
35
Comments
0
Likes
3
Embeds 0
No embeds

No notes for slide

Semantic Technology in Document Management

  1. 1. Washington DC, November 2011George Roth, Adonis Damianwww.recognos.com
  2. 2.  A document management system (DMS) is a computer system (or set of computer programs) used to track and store electronic documents and/or images of paper documents. It is usually also capable of keeping track of the different versions created by different users (history tracking). The term has some overlap with the concepts of content management systems. It is often viewed as a component of enterprise content management (ECM) systems and related to digital asset management, document imaging, workflow systems and records management systems. Make the formatted equivalent with non-formatted !November 2011
  3. 3. CLASSICAL NEW Metadata  Compliance Integration  Accessibility Capture  Interactivity Indexing  Augmentation Storage  Translation Retrieval  Linking – Relationships Distribution  Sentiment Analysis Security  New Search (Semantic Tagging, Deep Workflow Search, NL Questions) Collaboration Versioning Search Publishing …November 2011
  4. 4.  Volume Labor extensive The “research project” – 40% – 60% data gathering Metadata independent of content Shallow Search Hard to understand by non-expertsNovember 2011
  5. 5.  NLP Natural Language Processing – understand the meaning of documents (statistic, machine learning, hybrid, graph based) Semantic Search – tagging Data Integration Sentiment Analysis Linked Open Data – Linked Data Inference - ReasoningNovember 2011
  6. 6.  Inside – Controlled Environment - TRUST Inside – Security issues Same techniques as outside the enterprise Integrates non-formatted with formatted data Easy to measure the effects - ROI Add on to the existing KM models Emerging area – Semantic technologies started on the wwwNovember 2011
  7. 7. New features will become commodity in 2-3 years Compliance Data Extraction, Comparison, Change Analysis Interactivity Augmentation Translation Linking – Relationships Sentiment Analysis New Search (Semantic Tagging, Deep Search, NL Questions)November 2011
  8. 8.  Microsoft: Powerset (Bing), Fast Search, Jinni Google: Freebase, Needlebase Apple: SIRI Etc…November 2011
  9. 9.  Embedded Compliance RulesNovember 2011
  10. 10.  Example there is a rule: – email –Rule 0134C: “Not allowed to mention a percentage as a profit promise investing with the firm” In an email:“ Dear John, Our company has an amazing method to invest, so that you will make at least 10% profit in 3 months !!!! “ The email was stopped – sent to Compliance with the message: “Violation of the Rule 0134C”November 2011
  11. 11.  MFIP data extraction Link to the original documentNovember 2011
  12. 12.  Data Extraction, Comparison, Change AnalysisNovember 2011
  13. 13. November 2011
  14. 14. November 2011
  15. 15.  Create Alarm when Trading Policy Changes Create Alarm when Commissions Change (fields) Create Alarms when member of the Board ChangesNovember 2011
  16. 16.  InteractivityNovember 2011
  17. 17. November 2011
  18. 18.  AugmentationNovember 2011
  19. 19. November 2011
  20. 20.  Automated TranslationNovember 2011
  21. 21.  Google Translate  Great for simple translation – emails, non technical documents Language Weaver  Specialized translation through machine learning  Train the system per domainsNovember 2011
  22. 22.  Sentiment AnalysisNovember 2011
  23. 23.  Media Sentry Open Amplify, Expert Systems, Lymbix NLP and machine learningNovember 2011
  24. 24. November 2011
  25. 25.  SearchNovember 2011
  26. 26. November 2011
  27. 27. November 2011
  28. 28. November 2011
  29. 29. November 2011
  30. 30. November 2011
  31. 31. November 2011
  32. 32.  Complex App SamplesNovember 2011
  33. 33. November 2011
  34. 34. WWW Google Meltwaters Forums / Twitter Facebook Websites Alerts Alerts Blogs Exchange Server External Data Pull Exchange Twitter Facebook 80legs Diffbot Adapter Adapter Adapter Adapter Adapter Internal Message Storage File Server Natural Language Processing Uploaded ESSEX Taxonomy Web User Interface Data Storage MS SQL ServerNovember 2011
  35. 35.  Amdocs AIDA (AMDOCS Intelligent Decision Automation)November 2011
  36. 36. November 2011
  37. 37. Display Linked Data Ask a question – Entity Lookup semantic searchNovember 2011
  38. 38. November 2011
  39. 39. November 2011
  40. 40. November 2011
  41. 41. November 2011
  42. 42. November 2011
  43. 43. November 2011
  44. 44.  Interactive - Exists Search – Semantic Search, Q&A Semantic Tagging – Summarization LOD with domains Linked : People, Companies, Locations, Specific Terms Example a travel bookNovember 2011
  45. 45. The following technologies were used:- iQser – GIN- Clark & Parsia – Spanner, StarDog- Expert System – NLP- GATE- Smart Logic – Enterprise Query Platform – Fast Search – Microsoft Sharepoint 11- Revelytix- Cognition- Franz Systems- DiffBot- OntotextNovember 2011
  46. 46. George RothPresident and CEO Recognos Inc.San Franciscowww.recognos.comgroth@recognos.comDrew WarrenCEO Recognos FinancialNew Yorkdwarren@recognosfinancial.comwww.recognosfinancial.comNovember 2011
  1. A particular slide catching your eye?

    Clipping is a handy way to collect important slides you want to go back to later.

×