Knowledge Web meets Big Scholar

BigScholar 2015 keynote by Kuansan Wang (Microsoft Research), at WWW2015, Florence Italy. May 18 2015

Semantic SearchKnowledge GraphsBingISRCMicrosoft Academic
1.0x

Knowledge Web meets Big Scholar

Created 2 years ago

Duration 0:00:00
lesson view count 117
BigScholar 2015 keynote by Kuansan Wang (Microsoft Research), at WWW2015, Florence Italy. May 18 2015
Select the file type you wish to download
Slide Content
  1. Knowledge Web meets Big Scholar

    Slide 1 - Knowledge Web meets Big Scholar

    • BigScholar 2015 / WWW 2015
    • Kuansan Wang
    • Director, Internet Service Research Center
    • Microsoft Research, Redmond WA, USA
  2. “As we may think” (Vannevar Bush, 1945)

    Slide 2 - “As we may think” (Vannevar Bush, 1945)

  3. Source: http://w3.org/Proposal.html

    Slide 3 - Source: http://w3.org/Proposal.html

    • www.webat25.org
  4. Library of Alexandria

    Slide 4 - Library of Alexandria

    • 300 BC
  5. Hiro: 	Who worshipped Asherah?

    Slide 5 - Hiro: Who worshipped Asherah?

    • Librarian: Everyone who lived between India and Spain, from the second millennium B.C. up into the Christian era. With the exception of the Hebrews, who only worshipped her until the religious reforms....
    • Hiro: I thought the Hebrews were monotheists….
    • Librarian: Monolatrists. They did not deny the existence of other gods. Asherah was venerated as the consort of Yahweh.
    • Hiro: I don't remember anything about God having a wife in the Bible.
    • Librarian: The Bible didn't exist at that point. Judaism was just a loose collection of Yahwistic cults, each with different shrines and practices.
    • Hiro and the Librarian, Chapter 30, Snow Crash (1992) , Neal Stephenson
  6. In Ugarit

    Slide 6 - In Ugarit

    • In Egypt
    • In Israel and Judah
    • In Arabia
  7. Semantic Web

    Slide 8 - Semantic Web

    • (Tim Berners-Lee, 2000)
    • The “intelligent agent” that people have touted for ages will finally materialize.
  8. http://www.w3.org/2000/Talks/1206-xml2k-tbl/slide10-0.html

    Slide 9 - http://www.w3.org/2000/Talks/1206-xml2k-tbl/slide10-0.html

  9. Knowledge Web

    Slide 11 - Knowledge Web

    • Semantic Web
    • Human readable vs machine readable contents
    • Human defines standard for data formats and models
    • Explicit and precise specification of knowledge representation that everyone has to agree upon
    • Machine reads human readable contents
    • Machine learns to conflate different formats of the same thing
    • Latent and fuzzy representation of knowledge learned by mining big data
  10. Slide 12

    • TRADITIONAL
    • WEB SEARCH
    • Paradigm Shift in Web Search (the “Librarian”)
    • KNOWLEDGE
    • WEB SEARCH
    • Index Keywords in Documents
    • Digest World’s Knowledge
    • Match Keywords in Queries
    • Match User Intent
    • Relevance of “10 blue links”
    • Dialog Experience
    • “Bing Dialog Model: Knowledge, Intent and Dialog”, MSR Faculty Summit, July 2010
    • “Introducing the Knowledge Graph: things, not strings”, Official Google Blog, May 2012
    • “Chinese Search Engine – Baidu’s Practice”, SIRIP, SIGIR 2014, July 2014
  11. “Dialog Acts” in Bing/Cortana

    Slide 13 - “Dialog Acts” in Bing/Cortana

    • Answer
    • Confirmation
    • Disambiguation
    • Suggestion
    • Progressive: Refinement
    • Digressive: Recommendation (reactive + proactive)
  12. Answer

    Slide 14 - Answer

    • Confirmation
    • Confirmation
    • Refinement Dialog
    • Digressive Suggestion
  13. Confirmation

    Slide 15 - Confirmation

    • Answer
  14. Answer + Refinement Dialog as you type (aka “Page 0”)

    Slide 16 - Answer + Refinement Dialog as you type (aka “Page 0”)

  15. Confirmation Dialog

    Slide 17 - Confirmation Dialog

  16. Disambiguation Dialog at Page 0

    Slide 18 - Disambiguation Dialog at Page 0

  17. Disambiguation Dialog

    Slide 20 - Disambiguation Dialog

  18. Session Aware Suggestion

    Slide 21 - Session Aware Suggestion

  19. Multi-disciplinary Mash-up

    Slide 22 - Multi-disciplinary Mash-up

    • Knowledge representation
    • Scalable indexing
    • Transaction optimization
    • Federated Search
    • Relevance Ranking
    • Spam and fraud detection
    • Scalable System best practices
    • Statistical language model
    • Understanding and generation
    • Discourse and dialog management
    • Natural Language + Machine Learning
    • IR / Web Search
    • Database
  20. Advantages of Knowledge Web

    Slide 23 - Advantages of Knowledge Web

    • Machine doesn’t stop for biological functions
    • Machine has perfect memory
    • Machine gathers collective knowledge
    • Machine senses better
  21. How about Scholarly Work?

    Slide 26 - How about Scholarly Work?

  22. Slide 27

    • http://academic.research.microsoft.com
  23. http://searchengineland.com/bing-cortana-get-academic-search-integration-whole-new-level-196691

    Slide 30 - http://searchengineland.com/bing-cortana-get-academic-search-integration-whole-new-level-196691

  24. Slide 31

    • Institution (770K)
    • Paper (100M)
    • Venue (23K)
    • Event (26K)
    • Field of Study (50K)
    • Author (20M)
    • Microsoft Academic Graph
  25. Venue: “KDD”

    Slide 32 - Venue: “KDD”

    • Most Recent Event
    • Coming Event of the same Venue
    • Related Event of the same Field of Study
  26. NL Query Completion/Recommendation

    Slide 35 - NL Query Completion/Recommendation

    • How to complete never foreseen academic queries?
    • How to rank completion suggestions?
    • How to avoid making completions leading no search results?
  27. Finding reviewers/co-PI made easier

    Slide 36 - Finding reviewers/co-PI made easier

  28. Understanding a colleague made easier

    Slide 37 - Understanding a colleague made easier

  29. Quick Remarks on Ranking

    Slide 38 - Quick Remarks on Ranking

    • Page Rank: A paper is important if cited by important papers
    • Issues:
    • Citations take time to build up: biased against new publications
    • Citation contexts are ignored
    • “Link Spam”
    • Should make better use of heterogeneity of the graph
  30. Assessing Scholars and Their Work

    Slide 39 - Assessing Scholars and Their Work

    • Participate in the inaugural WSDM Cup
    • http://www.wsdm-conference.org/2016/calls.html#wsdm-cup
  31. Microsoft Academic Graph (MAG)

    Slide 40 - Microsoft Academic Graph (MAG)

    • New Release coming end of May 2015 on Azure
    • Free “Azure for Education” accounts
    • http://research.microsoft.com/MAG
  32. More Demo & Discussion at Microsoft BoothThank You!

    Slide 41 - More Demo & Discussion at Microsoft BoothThank You!