2. Bigger Picture
▪ LinkedIn’s vision
– Create economic opportunity for every member of the
global workforce
▪ Connect members to other members, knowledge and
opportunity and help them be great at what they do
4. Role of Search
▪ At the heart of the economic graph, search makes the
economic graph accessible, useful and actionable
▪ Powers searching people, jobs, companies, schools etc.
▪ On linkedin.com consumer, recruiter, sales solutions
4
11. Let’s talk intent - Navigational
▪ Navigational - exactly one result in mind
11
12. Two types of Intent - Exploratory
▪ Exploratory - Typically more than one entity in mind
12
13. How to handle navigational queries?
Be Fast
Type Less
Be Lenient
13
14. Handling Navigational Queries
▪ Type Less
– Index prefixes (‘ga’, ‘gan’, ‘gane’ => ‘ganesh’)
▪ Be Fast
– Do not retrieve all documents
– Order documents in posting list by static rank
– Modify query for targeted retrieval
▪ Be Lenient
– Smart spell correction
14
15. Exploratory Queries
▪ If possible guide users to more structured queries
▪ Above query could go into different verticals if these are selected
▪ User intent becomes much clearer
15
19. Query Processing - things not strings
1919
TITLE CO GEO
TITLE-237
software engineer
software developer
programmer
…
CO-1441
Google Inc.
Industry: Internet
GEO-7583
Country: US
Lat: 42.3482 N
Long: 75.1890 W
(RECOGNIZED TAGS: NAME, TITLE, COMPANY, SCHOOL, GEO, SKILL )
20. Retrieval
▪ Custom search engine to handle 100’s of millions of
documents (Galene)
▪ Key Features:
– Offline indexing pipeline
– Supports live updates with fine granularity
– Static Ranking
▪ Posting list organized by static rank for each
document
▪ Enables early termination
20
22. Ranking
▪ Manually tuning vs. Learning to Rank (LTR)
▪ Why Learning to Rank?
– Hard to manually tune with very large number of features
– Challenging to personalize
– LTR allows leveraging large volume of click data in an
automated way
22
30. Learning Algorithm
▪ Coordinate Ascent Algorithm
– Listwise approach
▪ Objective function: Normalized Discounted Cumulative
Gain (NDCG)
– Defined on graded relevance
– Intuition: more useful to show more-relevant documents at
higher positions
33. ▪ Why do we need this?
– Not to overwhelm the user with too much information
–Make results personally relevant
33
Motivation
34. ▪ Challenges
–Query can be ambiguous
–Incomparability across vertical objects
▪Compare objects of different nature: individual job vs. people cluster
▪Objects associate with different signals
34
Motivation
36. Learning Federation Model
▪ Predicts: p(click| individual result OR vertical cluster, query, searcher)
▪ Training data: click logs
▪ Features
–Relevance scores from base rankers
–Searcher intent
–Query intent
–etc.
37. Features
▪ Searcher Intents
– Mine searcher profiles and past behavior to infer intent
▪ Title recruiter -> recruiting intent
▪ Search for jobs -> job seeking intent
– Machine-learned models predict member intents:
▪Job seeking
▪Recruiting
▪Content consuming
37
38. Features
▪ Query Intents: e.g. p(job vertical| “software engineer”)
–Mine from historical searches and actions
38
39. Features
▪ Query Intents: e.g. p(job vertical| “software engineer”)
–Mine from historical searches and actions
▪ Personalized Query Intents
–p(job vertical| “software engineer”, searcher)
39
40. Features
▪ Query Intents: e.g. p(job vertical| “software engineer”)
–Mine from historical searches and actions
▪ Personalized Query Intents
–p(job vertical| “software engineer”, searcher)
–Individual searcher → searcher group
▪p(job vertical| “software engineer”, job seeking searcher)
40
42. Calibrate Signals across Verticals
▪ Relevance scores from vertical rankers are incomparable
▪ Construct composite features
People relevance score of searcher if result is People
f 1= ⎨0, otherwise
42
43. Calibrate Signals across Verticals
▪ Verticals associate with different signals
43
People Result
Job Result
Group Result
Recruiting
Intent
Job Seeking
Intent
Content
Consuming
Intent
44. Calibrate Signals across Verticals
▪ Verticals associate with different signals
44
People Result
Job Result
Group Result
Recruiting
Intent
Job Seeking
Intent
Content
Consuming
Intent
45. Calibrate Signals across Verticals
▪ Verticals associate with different signals
45
People Result
Job Result
Group Result
Recruiting
Intent
Job Seeking
Intent
Content
Consuming
Intent
46. Conclusions
▪ Search personalization is at the core of our economic graph
vision
–Connect talent with opportunity at massive scale
▪ Click data is useful sources for personalized training data
–Need to correct position bias
▪ Personalized features are keys
▪ Create composite features to calibrate across verticals