SlideShare a Scribd company logo
Submit Search
Upload
Login
Signup
Lecture 6: Watson and the Social Web (2014), Chris Welty
Report
Lora Aroyo
Follow
Professor Human Computer Interaction at Vrije Universiteit Amsterdam / VU
Mar. 16, 2014
•
0 likes
•
2,877 views
1
of
30
Lecture 6: Watson and the Social Web (2014), Chris Welty
Mar. 16, 2014
•
0 likes
•
2,877 views
Download Now
Download to read offline
Report
Technology
Lora Aroyo
Follow
Professor Human Computer Interaction at Vrije Universiteit Amsterdam / VU
Recommended
Janice Fraser, LUXr presentation at Lean Startup SXSW
500 Startups
2.9K views
•
48 slides
Eudora Welty
rlm67110
1.6K views
•
11 slides
Lecture 7: How to STUDY the Social Web? (2014)
Lora Aroyo
2K views
•
49 slides
Big, Open, Data and Semantics for Real-World Application Near You
Biplav Srivastava
1.2K views
•
84 slides
What is Watson – An Overvie.pdf
skyadav35
6 views
•
39 slides
Chatbots in 2017 -- Ithaca Talk Dec 6
Paul Houle
788 views
•
83 slides
More Related Content
Similar to Lecture 6: Watson and the Social Web (2014), Chris Welty
Ibm watson - how it works, and what it means for society beyond winning jeo...
Rick Bouter
1.1K views
•
45 slides
IBM Watson-How it works
Virginia Fernandez
2.5K views
•
45 slides
Watson how it works?
Ana Alves Sequeira
867 views
•
45 slides
Sis sat 1000 josh dreller
MediaPost
391 views
•
39 slides
Watson System
Pratik Kumar
3K views
•
44 slides
Upmc tpdev7
Jean-Yves Rigolet
13 views
•
65 slides
Similar to Lecture 6: Watson and the Social Web (2014), Chris Welty
(20)
Ibm watson - how it works, and what it means for society beyond winning jeo...
Rick Bouter
•
1.1K views
IBM Watson-How it works
Virginia Fernandez
•
2.5K views
Watson how it works?
Ana Alves Sequeira
•
867 views
Sis sat 1000 josh dreller
MediaPost
•
391 views
Watson System
Pratik Kumar
•
3K views
Upmc tpdev7
Jean-Yves Rigolet
•
13 views
Artificial intelligence
Sriharsha Koritala
•
895 views
Fix What Matters
Ed Bellis
•
678 views
IBM Watson: How it Works, and What it means for Society beyond winning Jeopardy!
Tony Pearson
•
15.6K views
HarambeeNet: Data by the people, for the people
Michael Bernstein
•
854 views
20211103 jim spohrer oecd ai_science_productivity_panel v5
ISSIP
•
146 views
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
Sri Ambati
•
4.2K views
Artificial Intelligence is back, Deep Learning Networks and Quantum possibili...
John Mathon
•
1.7K views
Step-by-step approach to question answering
NAVER Engineering
•
2.3K views
Sp14 cs188 lecture 1 - introduction
Amer Noureddin
•
492 views
Big data new physics giga om structure conference ny - march 2011
Jeff Jonas
•
3.4K views
The Near Future: AI in 2024
JosiahSeaman1
•
34 views
Spohrer SIRs 20230511 v16.pptx
ISSIP
•
20 views
AI Fables, Facts and Futures: Threat, Promise or Saviour
University of Hertfordshire
•
1.3K views
Crowdsourcing for Online Data Collection
Winter Mason
•
3.8K views
More from Lora Aroyo
CATS4ML Data Challenge: Crowdsourcing Adverse Test Sets for Machine Learning
Lora Aroyo
584 views
•
20 slides
Harnessing Human Semantics at Scale (updated)
Lora Aroyo
124 views
•
66 slides
Data excellence: Better data for better AI
Lora Aroyo
986 views
•
35 slides
CHIP Demonstrator presentation @ CATCH Symposium
Lora Aroyo
262 views
•
22 slides
Semantic Web Challenge: CHIP Demonstrator
Lora Aroyo
179 views
•
17 slides
The Rijksmuseum Collection as Linked Data
Lora Aroyo
1.9K views
•
26 slides
More from Lora Aroyo
(20)
CATS4ML Data Challenge: Crowdsourcing Adverse Test Sets for Machine Learning
Lora Aroyo
•
584 views
Harnessing Human Semantics at Scale (updated)
Lora Aroyo
•
124 views
Data excellence: Better data for better AI
Lora Aroyo
•
986 views
CHIP Demonstrator presentation @ CATCH Symposium
Lora Aroyo
•
262 views
Semantic Web Challenge: CHIP Demonstrator
Lora Aroyo
•
179 views
The Rijksmuseum Collection as Linked Data
Lora Aroyo
•
1.9K views
Keynote at International Conference of Art Libraries 2018 @Rijksmuseum
Lora Aroyo
•
832 views
FAIRview: Responsible Video Summarization @NYCML'18
Lora Aroyo
•
699 views
Understanding bias in video news & news filtering algorithms
Lora Aroyo
•
356 views
StorySourcing: Telling Stories with Humans & Machines
Lora Aroyo
•
726 views
Data Science with Humans in the Loop
Lora Aroyo
•
3.7K views
Digital Humanities Benelux 2017: Keynote Lora Aroyo
Lora Aroyo
•
2.4K views
DH Benelux 2017 Panel: A Pragmatic Approach to Understanding and Utilising Ev...
Lora Aroyo
•
4.3K views
Crowdsourcing ambiguity aware ground truth - collective intelligence 2017
Lora Aroyo
•
8.8K views
My ESWC 2017 keynote: Disrupting the Semantic Comfort Zone
Lora Aroyo
•
2.8K views
Data Science with Human in the Loop @Faculty of Science #Leiden University
Lora Aroyo
•
1.1K views
SXSW2017 @NewDutchMedia Talk: Exploration is the New Search
Lora Aroyo
•
17.7K views
Europeana GA 2016: Harnessing Crowds, Niches & Professionals in the Digital Age
Lora Aroyo
•
577 views
"Video Killed the Radio Star": From MTV to Snapchat
Lora Aroyo
•
617 views
UMAP 2016 Opening Ceremony
Lora Aroyo
•
475 views
Recently uploaded
h2 meet pdf test.pdf
JohnLee971654
51 views
•
4 slides
How to Manage Your Offshore Software Development Team Efficiently
Capital Numbers
28 views
•
15 slides
Orchestration, Automation and Virtualisation Maturity Model
CSUC - Consorci de Serveis Universitaris de Catalunya
51 views
•
19 slides
Cloud Composer workshop at Airflow Summit 2023.pdf
Leah Cole
74 views
•
80 slides
Enterprise Application and Data Protection on AWS with Amazon FSx for NetApp ...
LilyJang3
17 views
•
43 slides
Roottoo Innovation V24_CP.pdf
roottooinnovation
23 views
•
13 slides
Recently uploaded
(20)
h2 meet pdf test.pdf
JohnLee971654
•
51 views
How to Manage Your Offshore Software Development Team Efficiently
Capital Numbers
•
28 views
Orchestration, Automation and Virtualisation Maturity Model
CSUC - Consorci de Serveis Universitaris de Catalunya
•
51 views
Cloud Composer workshop at Airflow Summit 2023.pdf
Leah Cole
•
74 views
Enterprise Application and Data Protection on AWS with Amazon FSx for NetApp ...
LilyJang3
•
17 views
Roottoo Innovation V24_CP.pdf
roottooinnovation
•
23 views
Netwitness RT - Don’t scratch that patch.pptx
Stefano Maccaglia
•
89 views
LLaMA 2.pptx
RkRahul16
•
15 views
class and object in c++.pptx
Adarsh College, Hingoli
•
184 views
Unleashing Innovation: IoT Project with MicroPython
Vubon Roy
•
19 views
ISO Survey 2022: ISO 27001 certificates (ISMS)
Andrey Prozorov, CISM, CIPP/E, CDPSE. LA 27001
•
73 views
Enhance Productivity Expert Laptop Support For Modern Professional
IT Services Helps
•
15 views
Die ultimative Anleitung für HCL Nomad Web Administratoren
panagenda
•
57 views
Elevate Your Enterprise with FME 23.1
Safe Software
•
271 views
Keynote: Two years at the British Library... and counting / Alan Danskin (Bri...
CILIP MDG
•
22 views
Easy Salesforce CI/CD with Open Source Only - Dreamforce 23
NicolasVuillamy1
•
155 views
Mitigating Third-Party Risks: Best Practices for CISOs in Ensuring Robust Sec...
TrustArc
•
34 views
2023 Ivanti September Patch Tuesday
Ivanti
•
97 views
Knowledge graph use cases in natural language generation
Elena Simperl
•
83 views
Nymity Framework: Privacy & Data Protection Update in 7 States
TrustArc
•
117 views
Lecture 6: Watson and the Social Web (2014), Chris Welty
1.
© 2011 IBM
Corporation Watson and the Social Web Chris Welty IBM Watson Group ibmwatson.com Do Not Record. Do Not Distribute.
2.
© 2011 IBM
Corporation What is Cognitive Computing? § Increasingly, machines are being asked to add their computational power to problems which are not inherently solvable § Traditionally, these problems came from AI – The hardest AI problems are the easiest for human intelligence: vision, speech, natural language – these are not actually associated with “being intelligent” – Human intelligence provides solutions, but does not scale § Cognitive Computing is founded on four principles Learn & improve. Cognitive computing systems focus on inexact solutions to unsolvable problems that utilize machine learning and improve over time. Often they combine multiple approaches and must integrate them effectively. They must learn from humans, in more and more seamless ways. Speed&Scale. Cognitive computing harnesses the clear advantage machines have over humans in their ability to perform mundane tasks of arbitrary complexity repeatedly, whether it is the scale of the data or the complexity of the task. Interact in a natural way. Cognitive computing provides technologies that support a higher level of human cognition by adapting to human approaches and interfaces...over the next several decades it will incorporate essentially all the ways humans sense and interact. Assist & augment human cognition. Cognitive computing addresses problems that lie squarely in the province of human intelligence, but where we can't handle the volume of information, penetrate the complexity or otherwise extend our reach (physically). The goal is to be useful, not universally correct. or Computers can be incorrect and still prove useful!
3.
© 2011 IBM
Corporation Examples of Cognitive Computing § Web Search § Image Search § Event Search § Recommendations § Natural Language Processing
4.
© 2011 IBM
Corporation What is Watson? § Open Domain Question-Answering Machine § Given – Rich Natural Language Questions – Over a Broad Domain of Knowledge § Delivers – Precise Answers: Determine what is being asked & give precise response – Accurate Confidences: Determine likelihood answer is correct – Consumable Justifications: Explain why the answer is right – Fast Response Time: Precision & Confidence in <3 seconds – At the level of human experts – Proved its mettle in a televised match – Won a 2-game Jeopardy match against the all-time winners – viewed by over 50,000,000 4
5.
© 2011 IBM
Corporation What is Jeopardy? § Jeopardy! is an American quiz show – 1964 – Today – Household name in U.S. § answer-and-question format – contestants are presented with clues in the form of answers – must phrase their responses in question form. – Open domain trivia questions, speed is a big factor § Example – Category: General Science – Clue: When hit by electrons, a phosphor gives off electromagnetic energy in this form – Answer: What is light?
6.
© 2011 IBM
Corporation Social Computing: What’s the connection? § Social Web as Data Source: – The vast majority of sources Watson used to answer questions came from community-created data – Adapting Watson to a new problem requires the same kind of information about that problem § Social Machines: – Watson combined with people is a powerful proposition § Social Web as Application: – Watson’s major advance is in understanding natural language, the technology can be useful to augment social interaction
7.
© 2011 IBM
Corporation $200 If you are looking at the wainscoating, you are looking in this direction. $1000 The first person mentioned by name in ‘The Man in the Iron Mask’ is this hero of a previous book by the same author. 7 The Jeopardy! Challenge Hard for humans, hard for machines Broad/Open Domain Complex Language High Precision Accurate Confidence High Speed $600 In cell division, mitosis splits the nucleus & cytokinesis splits this liquid cushioning the nucleus $800 The conspirators against this man were wounded by each other while they stabbed at him But hard for different reasons. For people, the challenge is knowing the answer For machines, the challenge is understanding the question What is down? Who is D’Artagnan? What is cytoplasm? Who is Julius Caesar?
8.
© 2011 IBM
Corporation The Winner’s Cloud What It Takes to compete against Top Human Jeopardy! Players Winning Human Performance 2007 QA Computer System Grand Champion Human Performance Top human players are remarkably good. Each dot – actual historical human Jeopardy! games More Confident Less Confident Develop against a metric!
9.
© 2011 IBM
Corporation 2007 QA Computer System In 2007, we committed to making a Huge Leap! More Confident Less Confident Each dot – actual historical human Jeopardy! games Computers? Not So Good. Winning Human Performance Grand Champion Human Performance The Winner’s Cloud What It Takes to compete against Top Human Jeopardy! Players
10.
© 2011 IBM
Corporation DeepQA: The Technology Behind Watson An example of a new software paradigm . . . Answer Scoring Models Answer & Confidence Question Evidence Sources Models Models Models Models ModelsPrimary Search Candidate Answer Generation Hypothesis Generation Hypothesis and Evidence Scoring Final Confidence Merging & Ranking Synthesis Answer Sources Question & Topic Analysis Question Decomposition Evidence Retrieval Deep Evidence Scoring Hypothesis Generation Hypothesis and Evidence Scoring Learned Models help combine and weigh the Evidence DeepQA generates and scores many hypotheses using an extensible collection of Natural Language Processing, Machine Learning and Reasoning Algorithms. These gather and weigh evidence over both unstructured and structured content to determine the answer with the best confidence. Content from Community Resources!
11.
© 2011 IBM
Corporation Example Question In 1894 C.W. Post created his warm cereal drink Postum in this Michigan city Related Content (Structured & Unstructured) Primary Search 1985 Post Foods aramour General Foods Grand Rapids … Battle Creek … … Candidate Answer Generation 1) Battle Creek (0.85) 2) Post Foods ( 0.20) 3) 1985 (0.05) Merging & Ranking Evidence Retrieval Question Analysis Keywords: 1894, C.W. Post, created … Lexical AnswerType: (Michingan city) Date(1894) Relations: Create(Post, cereal drink) … [0.58 0 -1.3 … 0.97] [0.71 1 13.4 … 0.72] [0.12 0 2.0 … 0.40] [0.84 1 10.6 … 0.21] [0.33 0 6.3 … 0.83] [0.21 1 11.1 … 0.92] [0.91 0 -8.2 … 0.61] [0.91 0 -1.7 … 0.60] Evidence Scoring Need thousands of Q/A pairs for training!
12.
© 2011 IBM
Corporation Planet Fitness Role of Answer Typing in QA Type Information - a crucial hint to get the correct answer ASTRONOMY: In 1610 Galileo named the moons of this planet for the Medici brothers Telescope Giovanni Medici Sidereus Nuncius Jupiter Ganymede Telescope (Instrument) Giovanni Medici (Person) Sidereus Nuncius (Book) Jupiter (Planet) Ganymede (Moon) Terms Associated with Clue Context (e.g. via Keyword Search) Planet Fitness (Planet)
13.
© 2011 IBM
Corporation § This fish was thought to be exLnct millions of years ago unLl one was found off South Africa in 1938 § Category: ENDS IN "TH" § Answer: § When hit by electrons, a phosphor gives off electromagneLc energy in this form § Category: General Science § Answer: § Secy. Chase just submiXed this to me for the third Lme-‐-‐guess what, pal. This Lme I'm accepLng it § Category: Lincoln Blogs § Answer: The type of thing being asked for is often indicated but can go from specific to very vague coelacanth light (or photons) his resigna4on 13 Answer Typing for Jeopardy!?
14.
© 2011 IBM
Corporation Broad Domain Our Focus is on reusable NLP technology for analyzing vast volumes of as-is text. Structured sources (DBs and KBs) provide background knowledge for interpreting the text. We do NOT attempt to anticipate all questions and build databases. We do NOT try to build a formal model of the world
15.
© 2011 IBM
Corporation Sources for typing evidence § DbPedia & Freebase – Wide coverage of well-known entities – Taxonomy (MountainsOfNepal → Mountain) – Good type coverage, but not many synonyms • E.g. what about “summit” § Wikpedia Categories – Wide coverage of entities and type name synonyms – Noisy (many errors) § Wikipedia Intro – First sentence always indicates the most common type of the entity – Highly reliable, low coverage of types Communities can scale data collection!
16.
© 2011 IBM
Corporation Typing Impact on Jeopardy! clues 61.5% 62.0% 62.5% 63.0% 63.5% 64.0% 64.5% 65.0% 65.5% 66.0% 66.5% An ensemble of TyCor components + ~10%
17.
© 2011 IBM
Corporation Many sources of evidence In 1894 C.W. Post created his warm cereal drink Postum in this Michigan city Related Content (Structured & Unstructured) Primary Search 1985 Post Foods aramour General Foods Grand Rapids … Battle Creek … … Candidate Answer Generation 1) Battle Creek (0.85) 2) Post Foods ( 0.20) 3) 1985 (0.05) Merging & Ranking Evidence Retrieval Question Analysis Keywords: 1894, C.W. Post, created … Lexical AnswerType: (Michingan city) Date(1894) Relations: Create(Post, cereal drink) … [0.58 0 -1.3 … 0.97] [0.71 1 13.4 … 0.72] [0.12 0 2.0 … 0.40] [0.84 1 10.6 … 0.21] [0.33 0 6.3 … 0.83] [0.21 1 11.1 … 0.92] [0.91 0 -8.2 … 0.61] [0.91 0 -1.7 … 0.60] Evidence Scoring
18.
© 2011 IBM
Corporation Watson as part of a social machine § Watson makes mistakes: – This woman was the first to witness her husband resign from the U.S. Presidency. – This U.S. City’s largest airport is named for a world-war II hero; its second largest for a world-war II battle. § These mistakes are typically obvious to people – Even when they don’t know the answer – Watson isn’t stupid, it solves problems differently – Often these multiple perspectives can combine productively • E.g. add a “dismiss” button to the answer interface Richard Nixon Dolly Madison Pat Nixon Watson can adapt and learn from its users!
19.
© 2011 IBM
Corporation Cut to the chase….. Watson emerges victorious
20.
© 2011 IBM
Corporation Technology marches forward…
21.
© 2011 IBM
Corporation Adapt Watson Models Answer & Confidence Question Evidence Sources Models Models Models Models Models Answer Sources . . . Answer Scoring Primary Search Candidate Answer Generation Hypothesis Generation Hypothesis and Evidence Scoring Final Confidence Merging & Ranking Synthesis Question & Topic Analysis Question Decomposition Evidence Retrieval Deep Evidence Scoring Hypothesis Generation Hypothesis and Evidence Scoring Learned Models help combine and weigh the Evidence What does it take to use Watson in a new domain? (medical diagnosis, call centers, etc...) Gathering significant numbers of question-answer pairs is proving to be one of the most significant challenges for adapting Watson. Can the social web help? Community created!
22.
© 2011 IBM
Corporation Integrating Watson in Social Interaction? Did you hear about Bob? No He’s taking a year off to climb the tallest mountain! The tallest mountain is Mount Everest. Wow. me me Jeff Watson Jeff
23.
© 2011 IBM
Corporation Privacy – a blessing and a curse Need to protect our data, but… Crime on the web, the social web, is very real Identity theft Credit card, bank, insurance fraud Terrorist networks Medical diagnosis Monitoring your profile for health-related information ICT for depression Calendar, appointments, traffic, spreading disease
24.
© 2011 IBM
Corporation The arrival of Cognitive Computing Learn & improve. The core of Watson is a group of over 100 independent algorithms that approximate a solution to the “is this the right answer to the question” problem. Achieving winning (human expert) performance, required two hallmarks of cognitive computing systems: a metric to measure improvements to the system (the winners cloud), and a significant ground truth (over 200K Q-A pairs). Speed&Scale. Watson used big data, as well as a 3000 node cluster for massive computation to get answering speeds down into the 2s range. Interact in a natural way. Watson was a significant step forward in natural language understanding, the most basic interface for humans. Say goodbye to your mouse… Assist & augment human cognition. Watson depended on primarily a set of background documents (the corpus). The value of having access to this kind of fact-finding power over a large (and possibly changing) corpus provides a clear augmentation to human abilities.
25.
© 2011 IBM
Corporation The arrival of Cognitive Computing Learn & improve. The core of Watson is a group of over 100 independent algorithms that approximate a solution to the “is this the right answer to the question” problem. Achieving winning (human expert) performance, required two hallmarks of cognitive computing systems: a metric to measure improvements to the system (the winners cloud), and a significant ground truth (over 200K Q-A pairs). 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% % Answered
26.
© 2011 IBM
Corporation The arrival of Cognitive Computing Assist & augment human cognition. Watson depended on primarily a set of background documents (the corpus). The value of having access to this kind of fact-finding power over a large (and possibly changing) corpus provides a clear augmentation to human abilities. UTI Diabetes Influenza hypokalemia Renal failure esophogitis Diagnosis Models Confidence Most Confident Diagnosis: UTI Symptoms Tests/Findings Medica4ons Family History Notes/Hypotheses Huge Volumes of Texts, Journals, References, DBs etc. Pa4ent History
27.
© 2011 IBM
Corporation The arrival of Cognitive Computing Speed&Scale. Watson used big data, as well as a 3000 node cluster for massive computation to get answering speeds down into the 2s range.
28.
© 2011 IBM
Corporation The arrival of Cognitive Computing Interact in a natural way. Watson was a significant step forward in natural language understanding, the most basic interface for humans. Say goodbye to your mouse…
29.
© 2011 IBM
Corporation The arrival of Cognitive Computing Learn & improve. The core of Watson is a group of over 100 independent algorithms that approximate a solution to the “is this the right answer to the question” problem. Achieving winning (human expert) performance, required two hallmarks of cognitive computing systems: a metric to measure improvements to the system (the winners cloud), and a significant ground truth (over 200K Q-A pairs). Speed&Scale. Watson used big data, as well as a 3000 node cluster for massive computation to get answering speeds down into the 2s range. Interact in a natural way. Watson was a significant step forward in natural language understanding, the most basic interface for humans. Say goodbye to your mouse… Assist & augment human cognition. Watson depended on primarily a set of background documents (the corpus). The value of having access to this kind of fact-finding power over a large (and possibly changing) corpus provides a clear augmentation to human abilities.
30.
© 2011 IBM
Corporation …and for Social Web § First and foremost, social web analytics (e.g. recommendations) and Social Computing in general lie clearly in the realm of Cognitive Computing – Uncertainty, natural language, human intelligence – Inexact solutions that can improve with time, training – Problems & solutions need metrics to be solvable § All cognitive computing systems require ground truth data – This data is expensive to collect – Crowdsourcing is a key new technology/approach § The user interface moving closer to people – Natural language, speech, gestures – In addition, integrating the collection of training data seamlessly into the interface is a key development § Cognitive computing systems require integration of multiple, disparate, data sources – Structured, unstructured, semi-structured – curated, crowdsourced