Linking Today's Wikipedia and News from the Past PIKM 2014 The 7th - PowerPoint PPT Presentation

Linking Today's Wikipedia and News from the Past PIKM 2014 The 7th Workshop for Ph.D. Students at CIKM 2014 Shanghai, 3 November 2014 Arunav Mishra

Yesterday’s N EWS Today’s W IKIPEDIA & Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 2

What is the role of Germany in the Eurozone crisis? Mr. Busy (Journalist) Google News Wikipedia {Eurozone, crisis, Germany, role} {Eurozone, crisis, Germany, role} 7580 results I don’t understand..!!! Crtl + F ..!! Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 3

Lin ink Wik iki-Excerpts and News Artic icle les … On 16 June 2012 the European Central Bank together European Leaders to with other European leaders hammered out plans for the Present Plan to Quell ECB to become a bank regulator and to form a deposit the Crisis Quickly insurance program to augment national programs. Other economic reforms promoting European growth and Published: June 16, 2012 employment were also proposed. … Wiki-excerpts News Articles Wikipedia Article Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 4

Overview ✓ 1 Tasks and Challenges 2 Datasets, Benchmark, and Evaluation 3 Simplified Wiki2News 4 Approaches 5 Experiments 6 Summary Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 5

Lin inkin ing Wik ikip ipedia ia To News “How did it happen?” Challenges Wiki2News For a given Wiki-excerpt, retrieve ranked 1. Leveraging spatio-temporal list of past news articles providing details expressions in Wiki-excerpts 2. Leveraging references to entities in Wiki-excerpts 3. Bridging of vocabulary gap between news articles and Wiki-excerpts Input : A Wiki-excerpt Output : Ranked list of news articles Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 6

Lin inkin ing News To Wik ikip ipedia ia “How is it remembered?” News2Wiki Challenges For a given set of past news articles, 1. Reduction of verbosity of retrieve ranked list of Wiki-excerpts that the input news articles summarize the event 2. Estimating event span from specific news articles 3. Addressing change in language usage sentence construction, and spellings in historic news articles Input : Set of news articles Output : Ranked list of Wiki-excerpts Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 7

Overview 1 Tasks and Challenges ✓ 2 Datasets, Benchmark, and Evaluation 3 Simplified Wiki2News 4 Approaches 5 Experiments 6 Summary Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 8

Datasets • English Wikipedia dump and revision history • Latest released on 8 October 2014 dump is 10.52 GB compressed • The New York Times Annotated Corpus • 2 million documents published between 1987 and 2007 • ClueWeb 09/12 corpora • 2 billion web pages collected in 2009/2012 • Already-existing entity annotations Freebase and YAGO2 Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 9

Benchmark Wiki-excerpt : Existing citations as text boundaries • Refer to a single event or a story within a larger event • Validated by citations European Leaders to Boundaries Present Plan to Quell the Crisis Quickly ... three-year lending adventure (LTRO)". [243] By JACK EWING Published: June 16, 2012 Reorganization of the European banking system On 16 June 2012 the European Central Bank together with other European leaders hammered out plans for Link the ECB to become a bank regulator and to form a deposit insurance program to augment national programs. Other economic reforms promoting European growth and employment were also proposed. [244] Outright Monetary Transactions (OMTs)… Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 10

Statis istics • 5,536 excerpts from 4,882 articles linked to New York Times • Excerpts types based on length: Type Number of terms Number of excerpts Factual excerpts (Short) [1,20] 1,120 Paraphrased excerpts [21,50] 2,547 Wordy excerpts (Long) [51,400] 1,869 • 74.2% of the excerpts have temporal expressions • Day : on January 19 2000 • Month : in August 1994 • Year : in 1995 • Time Range : since February 1988 until March 1988 Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 11

Evalu luation • Leverage Wikipedia references to news articles contained in the New York Times corpus or ClueWeb 09/12 Wiki2News: Given Wiki-excerpt, target the New York Times articles that are referred News2Wiki: Given New York Times articles, target Wiki-excerpts that refer to them • Evaluation Metrics: • Mean Reciprocal Rank, Normalized Discounted Cumulative Gain, Precision, Recall Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 12

Overview 1 Tasks and Challenges 2 Datasets, Benchmark, and Evaluation ✓ 3 Simplified Wiki2News 4 Approaches 5 Experiments 6 Summary Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 13

Lin inkin ing Year Page Events to News 1987 Archives Books in Brief: Nonfiction This article is about the year 1987. For the October 31, 1999 By Tammy Sill Nesmith number, see 1987 (number). For other uses, Published: October 31, 1999 see 1987 (disambiguation). Aretha From These Roots. Events[edit] By Aretha Franklin and David Ritz. Villard, $25. ''I could hear the words my father had spoken to me when I was a child: 'One day January [edit] you will sing for kings and queens,' ''Aretha Franklin recalls about an early 1980's London gala attended by the Prince of Wales and the Queen Mother. She has also • January 1 – Frobisher Bay, Northwest Territories, sung in the White House for Presidents Jimmy Carter and Bill Clinton, although she turned down a ball in Monte Carlo for Princes Albert and Rainier and a performance changes its name to Iqaluit. for Queen Beatrix of the Netherlands. The reason? Her fear of flying. Franklin -- who is 57 years old, has won 15 Grammy Awards and in 1987 became the • January 2 – Chadian – Libyan conflict – Battle of Fada: first woman inducted into the Rock and Roll Hall of Fame (though her fear of flying also kept her from that ceremony) -- has written a self-congratulatory yet The Chadian army destroys a Libyan armored brigade. http://www.showbiz411.com/ entertaining autobiography. The fourth of five children born to a famous Baptist • January 3 – Aretha Franklin becomes the first woman preacher and a nurse's aide, she began singing gospel in her father's Detroit church. At the age of 14, she gave birth to the first of her four children. At 16, after the birth inducted into the Rock and Roll Hall of Fame. of her second child, she dropped out of high school. She writes openly of her two divorces and such failed romances as her on-and-off relationship with the • January 4 – 1987 Maryland train collision: Temptations' Dennis Edwards and with a man she refers to as Mr. Mystique: ''Because he is a public figure, I prefer to protect his privacy.'' However, she is open An Amtrak train en route from Washington, about her feuds with other singers, like Gladys Knight and Cissy Houston. Despite the emotional upheavals and financial problems, Franklin sang the aria ''Nessun D.C. to Boston, Massachusetts collides dorma'' at the 1998 Grammy telecast when Luciano Pavarotti took ill, and has with Conrail engines at Chase, Maryland, killing 16. recorded ''A Rose Is Still a Rose,'' written by Lauryn Hill, which seems the perfect ending for this bittersweet yet sassy chronicle. Tammy Sill Nesmith Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 14

Retrieval Task Goal: Given a query event , retrieve a ranked list of news articles providing details Ranked list of Documents Given, Query Event Books in Brief: Nonfiction January 3, 1987 Published: October 31, 1999 Aretha- From These Roots. retrieve Aretha Franklin …The reason? Her fear of flying. Franklin -- who is 57 years old, has becomes the first won 15 Grammy Awards and in 1987 woman inducted became the first woman inducted into the Rock and into the Rock and Roll Hall of Fame Roll Hall of Fame. (though her fear of flying also kept her from that ceremony) … Temporal expression : • Discrete notion of time where smallest unit equals 1 day • is an interval in time domain T, • Example: 1987 = [1987.01.01, 1987.12.31] Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 15

Overview 1 Tasks and Challenges 2 Datasets, Benchmark, and Evaluation 3 Simplified Wiki2News ✓ 4 Approaches 5 Experiments 6 Summary Tuesday, November 04, 2014 PIKM 2014: Linking Today's Wikipedia and News from the Past 16