APIDays 2018 - Artificial Intelligence APIs - A roadmap to psychohistory
1 like277 views
The document discusses building an accurate knowledge base that could enable psychohistory, a fictional science from Isaac Asimov's Foundation series that predicts human behavior at large scales. It analyzes current knowledge bases and finds they are inaccurate and lack standard formats. It provides tips for building a new knowledge base, including relying on standards, translating natural language accurately, and using reading comprehension techniques to understand multiple sentences. The goal is to create a knowledge base with accurate, relevant information in a consistent format that is readable by both humans and computers.
![19//
Wikipedia
Abraham Lincoln (February 12, 1809 – April 15, 1865) was an American statesman and lawyer who
served as the 16th President of the United States from March 1861 until his assassination in April
1865. Lincoln led the United States through its Civil War—its bloodiest war and perhaps its
greatest moral, constitutional, and political crisis.[2][3] In doing so, he preserved the Union,
paved the way for the abolition of slavery, strengthened the federal government, and modernized
the economy.
An astute politician deeply involved with power issues in each state, Lincoln reached out to the
War Democrats and managed his own re-election campaign in the 1864 presidential election.
Anticipating the war's conclusion, Lincoln pushed a moderate view of Reconstruction, seeking to
reunite the nation speedily through a policy of generous reconciliation in the face of lingering
and bitter divisiveness. On April 14, 1865, five days after the surrender of Confederate general
Robert E. Lee, Lincoln was shot by Confederate sympathizer John Wilkes Booth and died the next
day. Lincoln has been consistently ranked both by scholars[5] and the public[6] as among the
greatest U.S. presidents.](https://image.slidesharecdn.com/psychohistory-180206134444/85/APIDays-2018-Artificial-Intelligence-APIs-A-roadmap-to-psychohistory-19-320.jpg)
![30//
Tip n°4: Working from natural language using translation
Abraham Lincoln (February 12, 1809 – April 15, 1865)
was an American statesman and lawyer who served as the
16th President of the United States from March 1861 until
his assassination in April 1865. Lincoln led the United
States through its Civil War—its bloodiest war and perhaps
its greatest moral, constitutional, and political crisis. In
doing so, he preserved the Union, paved the way for the
abolition of slavery, strengthened the federal government,
and modernized the economy.
{
"name": "Abraham Lincoln",
"birthDate": "February 12, 1809",
"deathDate": "April 15, 1865",
"occupations": [
{
"roleName": "American statesman"
},
{
"roleName": "lawyer"
},
{
"roleName": "president of the United States",
"startDate": "March 1861",
"endDate": "April 1865"
}
],
"causeOfDeath": "assassination"
}](https://image.slidesharecdn.com/psychohistory-180206134444/85/APIDays-2018-Artificial-Intelligence-APIs-A-roadmap-to-psychohistory-30-320.jpg)
APIDays 2018 - Artificial Intelligence APIs - A roadmap to psychohistory
- 1. A roadmap to psychohistory or the insufficiency of current knowledge bases Paris, January 31, 2018
- 2. 2// What is psychohistory? Foundation is a science fiction book series written by American author Isaac Asimov. It won the one-time Hugo Award for "Best All-Time Series" in 1966. Psychohistory is a fictional science which combines history, sociology, and mathematical statistics to make general predictions about the future behavior of very large groups of people.
- 3. 3// It’s a machine learning problem Historical Data Training Prediction New Data Re-Training
- 4. 4// It’s a machine learning problem Corpus Algorithm Objective
- 5. 5// It’s a machine learning problem Corpus Algorithm Objective Can we find a corpus ?
- 6. 6// Problem of content vs form
- 7. 7// Problem of content vs form
- 9. 9// Missing data What we want in a knowledge base
- 10. 10// Missing data What we want in a knowledge base Accuracy
- 11. 11// Missing data What we want in a knowledge base Accuracy Relevance
- 12. 12// Missing data What we want in a knowledge base Accuracy Relevance Standard format
- 13. 13// Missing data What we want in a knowledge base Accuracy Relevance Standard format Readable by human and computer
- 14. 14// Looking at Google Knowledge Graph: Taylor Swift American singer-songwriter
- 15. 15// Looking at Google Knowledge Graph: Abraham Lincoln Assassination of Abraham Lincoln Abraham Lincoln
- 16. 16// Looking at Google Knowledge Graph: not that accurate...
- 19. 19// Wikipedia Abraham Lincoln (February 12, 1809 – April 15, 1865) was an American statesman and lawyer who served as the 16th President of the United States from March 1861 until his assassination in April 1865. Lincoln led the United States through its Civil War—its bloodiest war and perhaps its greatest moral, constitutional, and political crisis.[2][3] In doing so, he preserved the Union, paved the way for the abolition of slavery, strengthened the federal government, and modernized the economy. An astute politician deeply involved with power issues in each state, Lincoln reached out to the War Democrats and managed his own re-election campaign in the 1864 presidential election. Anticipating the war's conclusion, Lincoln pushed a moderate view of Reconstruction, seeking to reunite the nation speedily through a policy of generous reconciliation in the face of lingering and bitter divisiveness. On April 14, 1865, five days after the surrender of Confederate general Robert E. Lee, Lincoln was shot by Confederate sympathizer John Wilkes Booth and died the next day. Lincoln has been consistently ranked both by scholars[5] and the public[6] as among the greatest U.S. presidents.
- 20. 20// WikiData as a Rosetta Stone
- 21. 21// Wikipedia: Most important articles
- 22. 22// DBpedia <http://dbpedia.org/resource/Otter_Tail_County,_Minnesota> <http://www.w3.org/2000/01/rdf-schema#comment> "Otter Tail County is a county located in the U.S. state of Minnesota. As of the 2010 census, the population was 57,303. Its county seat is Fergus Falls. The county was formed in 1858 and organized in 1868. Otter Tail County comprises the Fergus Falls, MN Micropolitan Statistical Area."@en . <http://dbpedia.org/resource/Murray_County,_Minnesota> <http://www.w3.org/2000/01/rdf-schema#comment> "Murray County is a county located in the U.S. state of Minnesota. The population was 8,725 at the 2010 census. Its county seat is Slayton. The county was formed in 1857 and organized in 1872."@en .
- 23. 23// WikiData { "type": "item", "id": "Q91", "P734": [ { "mainsnak": { "snaktype": "value", "property": "P734", "hash": "228ea0386cc21946b31af3295de9965622a8d256", "datavalue": { "value": { "entity-type": "item", "numeric-id": 18610168, "id": "Q18610168" },
- 24. 24// WikiData { "family name" : "Lincoln", "given name" : "Abraham", "manner of death" : "homicide", "cause of death" : "ballistic trauma", "place of birth" : "LaRue County", "place of death" : "Washington, D.C.", "mother" : "Nancy Hanks Lincoln", "father" : "Thomas Lincoln", "child" : "Tad Lincoln", "place of burial" : "Springfield", "position held" : "member of the Illinois House of Representatives", "date of death" : "15 April 1865", "date of birth" : "12 February 1809", "member of political party" : "Whig Party",
- 25. 25// Accuracy Missing data Relevance Standard format Human/Machine readable Comparison chart
- 26. 26// Tips for building your own knowledge base
- 27. 27// Tip n°1: rely on existing standards for your ontologies
- 28. 28// Tip n°2: Careful about standards: ISO 8601 dates 2018-01-31T10:00:00Z Jan 31st, 2018, 10:00 AM UTC 2016-12-31T23:59:60Z Leap second 2018-01 January 2018 20 21st century 2018-01-31T10:00:00+14 Time zones are between -12 and +14 1969-07-20T20:18:00Z Ambiguous, because before 1970 10000-01-01 Not defined -0044-03-15 Not defined UK: Day after 1751-03-24 1752-03-25 Russia: 1918-01-31 1918-01-13
- 29. 29// Tip n°3: avoid knowledge graphs
- 30. 30// Tip n°4: Working from natural language using translation Abraham Lincoln (February 12, 1809 – April 15, 1865) was an American statesman and lawyer who served as the 16th President of the United States from March 1861 until his assassination in April 1865. Lincoln led the United States through its Civil War—its bloodiest war and perhaps its greatest moral, constitutional, and political crisis. In doing so, he preserved the Union, paved the way for the abolition of slavery, strengthened the federal government, and modernized the economy. { "name": "Abraham Lincoln", "birthDate": "February 12, 1809", "deathDate": "April 15, 1865", "occupations": [ { "roleName": "American statesman" }, { "roleName": "lawyer" }, { "roleName": "president of the United States", "startDate": "March 1861", "endDate": "April 1865" } ], "causeOfDeath": "assassination" }
- 31. 31// Tip n°5: Working from natural language with reading comprehension
- 32. 32// Working from natural language : reading comprehension REASONING DESCRIPTION EXAMPLE Lexical variation (synonymy) Major correspondences between the question and the answer sentence are synonyms. Q: What is the Rankine cycle sometimes called? Sentence: The Rankine cycle is sometimes referred to as a practical Carnot cycle. Lexical variation (world knowledge) Major correspondences between the question and the answer sentence require world knowledge to resolve. Q: Which governing bodies have veto power? S: The European Parliament and the Council of the European Union have powers of amendment and veto during the legislative process. Syntactic variation After the question is paraphrased into declarative form, its syntactic dependency structure does not match that of the answer sentence even after local modifications. Q: What Shakespeare scholar is currently on the faculty? S: Current faculty include the antimopologist Marshall Sahlins, ..., Shakespeare scholar David Bevington. Multiple sentence There is anaphora, or higher-level reasoning fusion of multiple sentences is required. Q: What collection does the V&A Theatre & Performance galleries hold? S: The V&A Theatre &Performance galleries opened in March 2009. They hold the UK’s biggest national collection of material about live performance.