1. #MozCon
Justin Briggs • Getty Images
Talking Back to Conversational Search
@justinrbriggs • justin.briggs@gettyimages.com

2. Working in SEO

8. Exciting time for SEO

9. Web Search
Page Page Page
Search in web, against documents

11. “What is limburger”

12. “Play say it ain’t so”

13. “Schedule a meeting with Lynn”

14. “Navigate to grandma’s house”

15. These queries never touch the web

16. Search
Web Email
Search against capabilities
Knowledge
Graph
Schema
Mobile
Apps
Documents Databases Applications

18. Understanding natural language
Breaking down strings
#1 Tokenization
#2 Parts of speech tagging
#3 Lemmatization
#4 Named entity detection

19. #1 Tokenization
Who directed pulp fiction

20. #2 Parts of speech tagging

21. #2 Parts of speech tagging
Who directed pulp fiction
WP VBD NNP
WP: wh-pronoun
VBD: verb, past tense
NNP: noun, proper, singular

22. #3 Lemmatization
am, are, is => be
car, cars, car’s, cars’ => car

23. #3 Lemmatization
Converting to canonical words

24. #4 Named entity detection
photos of Emma Watson

25. opennlp.apache.org
String tokens[] =
tokenizer.tokenize("An input sample sentence.");
"An", "input", "sample", "sentence", "."

26. opennlp.apache.org
Photos of Emma Watson
Photos of <START:person>Emma Watson<END>

27. Knowledge graph capability

28. Replicate using mql
https://www.googleapis.com/freebase/v1/
mqlread?query={<insert query here>}

29. 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?

30. 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

31. quepy.machinalis.com

33. Curating entity content

34. Attributes and connections
Emma Watson
Born: April 15, 1990 (age 24)
From: Paris, France

35. Which Brad Pitt?

36. Next level keyword targeting
Actor: actor, producer, Angelina Jolie, 1963, Fight Club
Boxer: martial arts, boxing, Olympics, 1981

37. Find common attributes by type

38. Dynamic targeting using entity attributes
<Name> (# <Number>) : <Position> for <Team>in <City>, <State>

39. 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
!

41. Marking up schema

42. Schema takes you from web to data

43. 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>

46. Exciting time for SEO

47. Feels like we’re over here

48. We’re actually over here

49. Getting to AI faster

50. #MozCon
Justin Briggs • Getty Images
@justinrbriggs • justin.briggs@gettyimages.com