Conversational Search, Entities, and Knowledge Graph - Mozcon 2014

10,778
-1

Published on

Talking Back to Conversational Search:
Looking at how conversational search and knowledge graph are changing how users search and engage with content, Justin will talk about implementing entities at enterprise scale. Justin is one of our four community speakers.

Published in: Marketing
3 Comments
47 Likes
Statistics
Notes
No Downloads
Views
Total Views
10,778
On Slideshare
0
From Embeds
0
Number of Embeds
20
Actions
Shares
0
Downloads
77
Comments
3
Likes
47
Embeds 0
No embeds

No notes for slide

Conversational Search, Entities, and Knowledge Graph - Mozcon 2014

  1. #MozCon Justin Briggs • Getty Images Talking Back to Conversational Search @justinrbriggs • justin.briggs@gettyimages.com
  2. Working in SEO
  3. Exciting time for SEO
  4. Web Search Page Page Page Search in web, against documents
  5. “What is limburger”
  6. “Play say it ain’t so”
  7. “Schedule a meeting with Lynn”
  8. “Navigate to grandma’s house”
  9. These queries never touch the web
  10. Search Web Email Search against capabilities Knowledge Graph Schema Mobile Apps Documents Databases Applications
  11. Understanding natural language Breaking down strings
 #1 Tokenization
 #2 Parts of speech tagging
 #3 Lemmatization #4 Named entity detection
  12. #1 Tokenization Who directed pulp fiction
  13. #2 Parts of speech tagging
  14. #2 Parts of speech tagging Who directed pulp fiction WP VBD NNP WP: wh-pronoun VBD: verb, past tense NNP: noun, proper, singular
  15. #3 Lemmatization am, are, is => be car, cars, car’s, cars’ => car
  16. #3 Lemmatization Converting to canonical words
  17. #4 Named entity detection photos of Emma Watson
  18. opennlp.apache.org String tokens[] = tokenizer.tokenize("An input sample sentence."); "An", "input", "sample", "sentence", "."
  19. opennlp.apache.org Photos of Emma Watson Photos of <START:person>Emma Watson<END>
  20. Knowledge graph capability
  21. Replicate using mql https://www.googleapis.com/freebase/v1/ mqlread?query={<insert query here>}
  22. Strings to things [{ "!/film/film/directed_by": [{ "/type/object/name": "pulp fiction", "/type/object/type": "/film/film" }], "/type/object/name": [{}], "/type/object/type": "/people/person" }] Question: Who directed the movie Pulp Fiction?
  23. Answering queries without pages { "result": [ { "!/film/film/directed_by": [ { "/type/object/type": "/film/film", "/type/object/name": "Pulp Fiction" } ], "/type/object/type": "/people/person", "/type/object/name": [ { "lang": "/lang/en", "type": "/type/text", "value": "Quentin Tarantino" } Answer: Quentin Tarantino
  24. quepy.machinalis.com
  25. Curating entity content
  26. Attributes and connections Emma Watson Born: April 15, 1990 (age 24) From: Paris, France
  27. Which Brad Pitt?
  28. Next level keyword targeting Actor: actor, producer, Angelina Jolie, 1963, Fight Club Boxer: martial arts, boxing, Olympics, 1981
  29. Find common attributes by type
  30. Dynamic targeting using entity attributes <Name> (# <Number>) : <Position> for <Team>in <City>, <State>
  31. Dynamic targeting using categories Emma Watson Photos - News, Publicity, Event, & Premiere Pictures ! Seattle Seahawks Photos - Team, Player, & Fan Pictures ! Justin Bieber Photos - News, Concert, & Fan Pictures !
  32. Marking up schema
  33. Schema takes you from web to data
  34. JSON-LD: JSON-based linked data format <script type="application/ld+json"> { "@context": "http://schema.org", "@type": "Person", "name": "John Doe", "jobTitle": "Graduate research assistant", "affiliation": "University of Dreams", "url": "http://www.example.com", "address": { "@type": "PostalAddress", "streetAddress": "1234 Peach Drive", "addressLocality": "Wonderland", "addressRegion": "Georgia" } } </script>
  35. Exciting time for SEO
  36. Feels like we’re over here
  37. We’re actually over here
  38. Getting to AI faster
  39. #MozCon Justin Briggs • Getty Images @justinrbriggs • justin.briggs@gettyimages.com

×