Text Analytic Summit 2010
2 likes912 views
The document discusses the Semantic Web and Linked Open Data, emphasizing the role of Freebase as a socially managed semantic database containing numerous entities and relations. It highlights the challenges of polysemy and the need for effective reconciliation and entity resolution across various vocabularies. Additionally, it addresses the integration of explicit semantics in web content using technologies like RDFa and microdata to enhance information accessibility.
![{
"/type/object/name":"Blade Runner",
"/type/object/type":"/film/film",
"/film/film/starring/actor":["Harrison Ford", "Rutger Hauer"],
"/film/film/director":"Ridley Scott",
"/film/film/release_date_s":"1981"
} [{
"id":"/guid/9202a8c04000641f8000000000009e89",
"name":["Blade Runner", "Bladerunner"],
"score":1.4320519,
"match":true,
"type":["/common/topic", "/film/film","/media_common/adapted_work", "/award/
award_winning_work",
......
]},
{
"id":"/guid/9202a8c04000641f80000000002643d0",
"name":["Blade"],
"score":0.48852453,
"match":false,
"type":["/common/topic", "/film/film", "/award/award_winning_work", "/award/
award_nominated_work",
.......
]},
{
"id":"/guid/9202a8c04000641f800000000e5daaae",
"name":["Blade"],
"score":0.46398318,
"match":false,
.....
http://data.labs.freebase.com/recon/](https://image.slidesharecdn.com/text-analytic-summit-100529145444-phpapp02/85/Text-Analytic-Summit-2010-36-320.jpg)
Text Analytic Summit 2010
- 1. It's not what you said, it's how you said it. Jamie Taylor, Ph.D. Text Analytic Summit Boston 2010
- 2. What do y'all mean "Semantics" The Web! Now with Better Flavor!
- 6. Tim Berners-Lee, James Hendler and Ora Lassila May 2001
- 7. The Semantic Web? The Cake taken from http://www.w3.org/2007/Talks/0130-sb-W3CTechSemWeb/layerCake-4.png
- 9. The Real Web http://en.wikipedia.org/wiki/File:Internet_map_1024.jpg
- 11. Wish it were real
- 12. Might be real
- 13. Is real, but don't believe it
- 15. Entities
- 16. Identifiers Side Step Polysemy Bono, A.K.A. Paul David Hewson http://rdf.freebase.com/ns/en.paul_david_hewson
- 17. Vocabulary Manufactures http://rdf.freebase.com/ns/automotive.make.model_s
- 18. A socially managed semantic database
- 19. Freebase has Many Types of Things
- 22. Many Strong Identifiers http://rdf.freebase.com/ns/en.berlin_wall http://www.ellerdale.com/topics/view/0080-6ba0 http://www.bbc.co.uk/music/artists/7f347782-eb14-40c3-98e2-17b6e1bfe56c http://musicbrainz.org/artist/7f347782-eb14-40c3-98e2-17b6e1bfe56c http://rdf.freebase.com/ns/authority.musicbrainz.7f347782-eb14-40c3-98e2-17b6e1bfe56c
- 23. 12 Million Entites 350 Million Relations
- 24. Users contribute data Users extend the data model
- 26. 1500 types with 500+ instances!! A range of of vocabularies....
- 27. Growing Freebase
- 28. Reconciliation +=
- 29. Reconciliation Relational Learning Record Matching Collective Entity Resolution Equivalence Mining Record Linking Identity Matching
- 30. Reconciliation "Excuse Me" "Excuse Me" "Harrison Ford" "Harrison Ford" "Vanity Fair" "Maytime"
- 31. Reconciliation "Fugitive" "Excuse Me" "Harrison Ford" "Harrison Ford" "Vanity Fair" "Blade Runner"
- 32. A Graph of Entities
- 33. Vocabulary contains located performed-at released-by created plays-in plays-in nationality education education located
- 35. Reconciliation as "understanding" contains located performed-at released-by created plays-in plays-in nationality education education located
- 36. { "/type/object/name":"Blade Runner", "/type/object/type":"/film/film", "/film/film/starring/actor":["Harrison Ford", "Rutger Hauer"], "/film/film/director":"Ridley Scott", "/film/film/release_date_s":"1981" } [{ "id":"/guid/9202a8c04000641f8000000000009e89", "name":["Blade Runner", "Bladerunner"], "score":1.4320519, "match":true, "type":["/common/topic", "/film/film","/media_common/adapted_work", "/award/ award_winning_work", ...... ]}, { "id":"/guid/9202a8c04000641f80000000002643d0", "name":["Blade"], "score":0.48852453, "match":false, "type":["/common/topic", "/film/film", "/award/award_winning_work", "/award/ award_nominated_work", ....... ]}, { "id":"/guid/9202a8c04000641f800000000e5daaae", "name":["Blade"], "score":0.46398318, "match":false, ..... http://data.labs.freebase.com/recon/
- 37. Data Everywhere
- 40. Wikipedia Features X X Error Prone -- Usually <99%
- 45. (Machine) Learning Semantics get 5M type types assertions 2.8M Wikipedia topics intersect the two calculate feature join feature counts generate type sources counts per type with topics scores for topics 2.4M features 1.6G scores 1400 types extract features 37M features 5M articles WEX
- 46. /people/person distribution untyped topics person topics other topics all topics Data courtesy Viral Shah
- 47. RABJ: Humans in the loop
- 48. Thresholding Results 99% threshold at 16.75
- 49. /people/person assertions threshold 53K /people/person assertions
- 50. Training Wheels? Semantics are Everywhere
- 53. A Strong Tag for Food Inc. http://movi.es/BVl43
- 60. Rich Snippets <div class="post-item restaurant-gen-info hreview-aggregate"> <div class="item vcard"> <h1 class="fn org">Taylor's Refresher</h1> <div class="address"> <div class="ratings"> <ul class="star-rating-2 rating" title="4.0 star rating across 3 ratings"> <li class="current-rating average" style="width:80%;">4.0 star rating</li> <li class="star"> </li> <li class="star"> </li><li class="star"> </li> <li class="star"> </li> <li class="star"> </li> </ul> <div class="rating-stats"> <span class="rating"> <span class="average">4.0</span> </span> rating over <span class="count">1</span> review </div>
- 62. RDFa microformats HTML5 MicroData Open Graph Protocol
- 63. Explicit Semantics in Surprising Places
- 66. Widget Microdata <div class="fb-widget" id="fbtb-9a1f44348ad145b5b7d7d7d2376b0420" style="border:0; outline:0; padding:0; margin:0; position:relative;" itemscope="" itemid="http:// www.freebase.com/id/en/taylor_swift" itemtype="http://www.freebase.com/id/music/ artist"> ..... </div>
- 68. "Vocabulary" Pattern taw shooter marksman marble marksman http://wordnet.freebaseapps.com photo: http://sarabbit.openphoto.net
- 70. Review (neighborhood) Pattern Eric Schlosser E. Coli Michael Pollan Robert Kenner