A Computer Called "Watson"

LondonJS talk on the technology behind IBM Watson.

Transcript

1. A Computer Called “Watson” James Thomas, IBM Emerging Tech COVER PHOTO Add cover photo Monday, 17 September 2012
2. GARY KASPAROV VERSUS “DEEP BLUE” MAY 1997 Monday, 17 September 2012
3. BLUE GENE DECEMBER 1999 Monday, 17 September 2012
4. “Fast forward to 2004...” Monday, 17 September 2012
5. JEOPARDY QUIZ SHOW Monday, 17 September 2012
6. KEN JENNINGS CHAMPION OF CHAMPIONS Monday, 17 September 2012
7. KEN JENNINGS CHAMPION OF CHAMPIONS KEN’S PERFORMANCE Monday, 17 September 2012
8. What if we build a computer to play Jeopardy? Monday, 17 September 2012
9. What if we build a computer to play Jeopardy? It’s way too hard Monday, 17 September 2012
10. Jeopardy! Finite, mathematically defined search space Limited number of moves and states Symbols completed grounded in mathematical rules of the games Chess Enormous problem domain and search space Source material is inherently unstructured information Advanced natural language processing Monday, 17 September 2012
11. BASELINE PERFORMANCE INITIAL EXPERIMENT Monday, 17 September 2012
12. “Fast forward to 2007...” Monday, 17 September 2012
13. DR. DAVID FERRUCCI - “WATSON” TEAM DIRECTOR 2007 - 2011 Monday, 17 September 2012
14. SIMULATING JEOPARDY! MATCHES Monday, 17 September 2012
15. BASELINE PERFORMANCE INITIAL EXPERIMENT Monday, 17 September 2012
16. WATSON WAS READY FEBRUARY 2011 Monday, 17 September 2012
17. Watson Jeopardy! Challenge February 14-16 2011. Ken Jennings Brad Rutter Monday, 17 September 2012
18. WATSON 1 - HUMANS 0 FEBRUARY 16, 2011 Monday, 17 September 2012
19. “Its largest airport is named for a WWII hero; its second largest, for a WWII battle” Category: US Cities Monday, 17 September 2012
20. “Its largest airport is named for a WWII hero; its second largest, for a WWII battle” Category: US Cities Watson: Toronto Monday, 17 September 2012
21. How does it work? Monday, 17 September 2012
22. WATSON ARCHITECTURE - DEEPQA MASSIVELY PARALLEL PROBABILISTIC EVIDENCE-BASED ARCHITECTURE Monday, 17 September 2012
23. DEEPQA ARCHITECTURE PHASES Question Analysis Primary Search Candidate Answer Generation Evidence Retrieval Evidence Scoring Merging and Ranking Monday, 17 September 2012
24. DEEPQA ARCHITECTURAL PHASES QUESTION ANALYSIS CATEGORY: CAPITALS QUESTION: WHAT IS THE CAPITAL OF SAMOA? Monday, 17 September 2012
25. DEEPQA ARCHITECTURAL PHASES QUESTION ANALYSIS CATEGORY: POETS & POETRY QUESTION: HE WAS A BANK CLERK IN THE YUKON BEFORE HE PUBLISHED “SONGS OF SOURDOUGH” IN 1907. Monday, 17 September 2012
26. DEEPQA ARCHITECTURAL PHASES QUESTION ANALYSIS CATEGORY: POETS & POETRY QUESTION: HE WAS A BANK CLERK IN THE YUKON BEFORE HE PUBLISHED “SONGS OF SOURDOUGH” IN 1907. DISCOVER: FOCUS Monday, 17 September 2012
27. DEEPQA ARCHITECTURAL PHASES QUESTION ANALYSIS CATEGORY: POETS & POETRY QUESTION: HE WAS A BANK CLERK IN THE YUKON BEFORE HE PUBLISHED “SONGS OF SOURDOUGH” IN 1907. DISCOVER: LEXICAL ANSWER TYPE Monday, 17 September 2012
28. DEEPQA ARCHITECTURAL PHASES QUESTION ANALYSIS CATEGORY: POETS & POETRY QUESTION: HE WAS A BANK CLERK IN THE YUKON BEFORE HE PUBLISHED “SONGS OF SOURDOUGH” IN 1907. DISCOVER: RELATIONSHIPS Monday, 17 September 2012
29. DEEPQA ARCHITECTURAL PHASES QUESTION ANALYSIS CATEGORY: POETS & POETRY QUESTION: HE WAS A BANK CLERK IN THE YUKON BEFORE HE PUBLISHED “SONGS OF SOURDOUGH” IN 1907. DISCOVER: QUESTION CLASS Monday, 17 September 2012
30. DEEPQA ARCHITECTURAL PHASES HYPOTHESIS GENERATION Hypothesis generation consists of two phases... Monday, 17 September 2012
31. DEEPQA ARCHITECTURAL PHASES HYPOTHESIS GENERATION Primary Search Monday, 17 September 2012
32. DEEPQA ARCHITECTURAL PHASES HYPOTHESIS GENERATION Data Sources - Unstructured Wikipedia IMDb Encyclopaedias Dictionaries Thesauri Literary Works Newswire Articles Monday, 17 September 2012
33. DEEPQA ARCHITECTURAL PHASES HYPOTHESIS GENERATION Data Sources - Structured DBpedia Wordnet YAGO Monday, 17 September 2012
34. DEEPQA ARCHITECTURAL PHASES HYPOTHESIS GENERATION Candidate Answer Generation Monday, 17 September 2012
35. DEEPQA ARCHITECTURAL PHASES EVIDENCE RETRIEVAL Watson then searches for additional evidence... Monday, 17 September 2012
36. DEEPQA ARCHITECTURAL PHASES EVIDENCE SCORING Deep Scoring Monday, 17 September 2012
37. DEEPQA ARCHITECTURAL PHASES EVIDENCE SCORING 0 0.25 0.5 0.75 1 Temporal Geospatial LAT Popularity Deep Scoring Christopher Columbus Vasco De Gamma Monday, 17 September 2012
38. DEEPQA ARCHITECTURAL PHASES FINAL MERGING AND RANKING Answer Merging Monday, 17 September 2012
39. DEEPQA ARCHITECTURAL PHASES FINAL MERGING AND RANKING Answer Merging Monday, 17 September 2012
40. DEEPQA ARCHITECTURAL PHASES FINAL MERGING AND RANKING Answer Ranking ISAAC NEWTON [0.10, 0.45 ... 0.78, 0.12] ??? ANSWER SCORES RANK EDMOND HALLEY [0.31, 0.52 ... 0.08, 0.72] ??? WILHELM TEMPEL [0.21, 0.54 ... 0.18, 0.92] ??? PETER SELLERS [0.14, 0.04 ... 0.25, 0.41] ??? Monday, 17 September 2012
41. DEEPQA ARCHITECTURAL PHASES FINAL MERGING AND RANKING Monday, 17 September 2012
42. DEEPQA ARCHITECTURAL PHASES FINAL MERGING AND RANKING Answer Ranking ISAAC NEWTON [0.10 ... 0.12] 3 ANSWER SCORES RANK EDMOND HALLEY [0.31 ... 0.72] 1 WILHELM TEMPEL [0.21 ... 0.92] 2 PETER SELLERS [0.14 ... 0.41] 4 0.14 CONFIDENCE 0.78 0.34 0.04 Monday, 17 September 2012
43. DEEPQA PERFORMANCE SCALING CHALLENGES Need to answer within a few seconds.... Monday, 17 September 2012
44. DEEPQA PERFORMANCE SCALING CHALLENGES Need to answer within a few seconds.... Early implementation took over two hours Monday, 17 September 2012
45. SCALING WATSON Monday, 17 September 2012
46. WATSON HARDWARE NINETY POWER 750 SERVERS 2880 POWER7 PROCESSOR CORES 16 TERABYTES OF RAM Monday, 17 September 2012
47. WATSON 1 - HUMANS 0 FEBRUARY 16, 2011 Monday, 17 September 2012
48. PUTTING WATSON TO WORK What’s next? Monday, 17 September 2012
49. PUTTING WATSON TO WORK HEALTHCARE Monday, 17 September 2012
50. QUESTIONS? Monday, 17 September 2012