Conversational Search, Entities, and Knowledge Graph - Mozcon 2014
Upcoming SlideShare
Loading in...5
×
 

Conversational Search, Entities, and Knowledge Graph - Mozcon 2014

on

  • 6,238 views

Talking Back to Conversational Search: ...

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.

Statistics

Views

Total Views
6,238
Views on SlideShare
5,247
Embed Views
991

Actions

Likes
43
Downloads
43
Comments
3

16 Embeds 991

https://twitter.com 568
https://www.linkedin.com 193
http://www.conseilsmarketing.com 77
http://www.promodo.com 70
http://www.linkedin.com 27
http://www.paperblog.fr 18
https://www.nexus.uanl.mx 12
http://www.slideee.com 7
https://tweetdeck.twitter.com 5
http://www.conferize.com 4
http://inbound.org 4
https://storify.com 2
http://www.google.co.uk 1
http://www.google.com 1
https://www.rebelmouse.com 1
http://tweetedtimes.com 1
More...

Accessibility

Categories

Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

Conversational Search, Entities, and Knowledge Graph - Mozcon 2014 Conversational Search, Entities, and Knowledge Graph - Mozcon 2014 Presentation Transcript

  • #MozCon Justin Briggs • Getty Images Talking Back to Conversational Search @justinrbriggs • justin.briggs@gettyimages.com
  • Working in SEO
  • Exciting time for SEO
  • Web Search Page Page Page Search in web, against documents
  • “What is limburger”
  • “Play say it ain’t so”
  • “Schedule a meeting with Lynn”
  • “Navigate to grandma’s house”
  • These queries never touch the web
  • Search Web Email Search against capabilities Knowledge Graph Schema Mobile Apps Documents Databases Applications
  • Understanding natural language Breaking down strings
 #1 Tokenization
 #2 Parts of speech tagging
 #3 Lemmatization #4 Named entity detection
  • #1 Tokenization Who directed pulp fiction
  • #2 Parts of speech tagging
  • #2 Parts of speech tagging Who directed pulp fiction WP VBD NNP WP: wh-pronoun VBD: verb, past tense NNP: noun, proper, singular
  • #3 Lemmatization am, are, is => be car, cars, car’s, cars’ => car
  • #3 Lemmatization Converting to canonical words
  • #4 Named entity detection photos of Emma Watson
  • opennlp.apache.org String tokens[] = tokenizer.tokenize("An input sample sentence."); "An", "input", "sample", "sentence", "."
  • opennlp.apache.org Photos of Emma Watson Photos of <START:person>Emma Watson<END>
  • Knowledge graph capability
  • Replicate using mql https://www.googleapis.com/freebase/v1/ mqlread?query={<insert query here>}
  • 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?
  • 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
  • quepy.machinalis.com
  • Curating entity content
  • Attributes and connections Emma Watson Born: April 15, 1990 (age 24) From: Paris, France
  • Which Brad Pitt?
  • Next level keyword targeting Actor: actor, producer, Angelina Jolie, 1963, Fight Club Boxer: martial arts, boxing, Olympics, 1981
  • Find common attributes by type
  • Dynamic targeting using entity attributes <Name> (# <Number>) : <Position> for <Team>in <City>, <State>
  • 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 !
  • Marking up schema
  • Schema takes you from web to data
  • 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>
  • Exciting time for SEO
  • Feels like we’re over here
  • We’re actually over here
  • Getting to AI faster
  • #MozCon Justin Briggs • Getty Images @justinrbriggs • justin.briggs@gettyimages.com