Lucene/Solr Revolution 2015

1. O C T O B E R 1 3 - 1 6 , 2 0 1 6 • A U S T I N , T X

2. Implementing Conceptual Search in Solr
Simon Hughes
Chief Data Scientist, Dice.com

3. 3
• Chief Data Scientist at Dice.com, under Yuri Bykov
• Key Projects involving Solr:
Who Am I?
• Recommender Systems – more jobs like this, more seekers like
this (uses custom Solr index)
• Custom Dice Solr MLT handler (real-time recommendations)
• Did you mean functionality
• Title, skills and company type-ahead
• Relevancy improvements in dice jobs search

4. 4
• Supply Demand Analysis
• Dice Skills pages – http://www.dice.com/skills
Other Projects
PhD
• PhD candidate at DePaul University, studying natural language processing and
machine learning

7. 7
Q. What is the Most Common Relevancy Tuning Mistake?

8. 8
Q. What is the Most Common Relevancy Tuning Mistake?
A. Ignoring the importance of RECALL

9. 9
Relevancy Tuning
• Key performance metrics to measure:
• Precision
• Recall
• F1 Measure - 2*(P*R)/(P+R)
• Precision is easier – correct mistakes in the top search results
• Recall - need to know which relevant documents don’t come back
• Hard to accurately measure
• Need to know all the relevant documents present in the index

10. 10
What is Conceptual Search?
• A.K.A. Semantic Search
• Two key challenges with keyword matching:
• Polysemy: Words have more than one meaning
• e.g. engineer – mechanical? programmer? automation engineer?
• Synonymy: Many different words have the same meaning
• e.g. QA, quality assurance, tester; VB, Visual Basic, VB.Net
• Other related challenges -
• Typos, Spelling Errors, Idioms
• Conceptual search attempts to solve these problems by learning concepts

11. 11
Why Conceptual Search?
• We will attempt to improve recall without diminishing precision
• Can match relevant documents containing none of the query terms

12. 12
Concepts
• Conceptual search allows us to retrieve documents by how similar the concepts
in the query are to the concepts in a document
• Concepts represent important high-level ideas in a given domain (e.g. java
technologies, big data jobs, helpdesk support, etc)
• Concepts are automatically learned from documents using machine learning
• Words can belong to multiple concepts, with varying strengths of association
with each concept

13. 13
Traditional Techniques
• Many algorithms have been used for concept learning, include LSA (Latent
Semantic Analysis), LDA (Latent Dirichlet Allocation) and Word2Vec
• All involve mapping a document to a low dimensional dense vector (an array
of numbers)
• Each element of the vector is a number representing how well the document
represents that concept
• E.g. LSA powers the similar skills found in dice’s skills pages

14. 14
Traditional Techniques Don’t Scale
• LSALSI, LDA and related techniques rely on factorization of very large term-
document matrices – very slow and computationally intensive
• Require embedding a machine learning model with the search engine to
map new queries to the concept space (latent or topic space)
• Query performance is very poor – unable to utilize the inverted index as all
documents have the same number of concepts
• What we want is a way to map words not documents to concepts. Then we
can embed this in Solr via synonym filters and custom query parsers

15. 15
Word2Vec and ‘Word Math’
• Word2Vec was developed by google around 2013 for learning vector
representations for words, building on earlier work from Rumelhart, Hinton
and Williams in 1986 (see paper below for citation of this work)
• Word2Vec Paper:
Efficient Estimation of Word Representations in Vector Space
• It works by training a machine learning model to predict the words
surrounding a word in a sentence
• Similar words get similar vector representations

16. 16
“Word Math” Example
• Using basic vector arithmetic, you get some interesting patterns
• This illustrates how it represents relationships between words
• E.g. man – king + woman = queen

17. 17
The algorithm learns to
represent different types
of relationships between
words in vector form

18. 18
At this point you may be thinking…

19. 19

20. 20
Why Do I Care? This is a Search Conference…

21. 21
Why Do I Care? This is a Search Conference…
• This algorithm can be used to represent documents as vectors of concepts
• We can them use these representations to do conceptual search
• This will surface many relevant documents missed by keyword matching
• This boosts recall
• This technique can also be used to automatically learn synonyms

22. 22
A Quick Demo
Using our Dice.com active jobs index, some example common user queries:
• Data Scientist
• Big Data
• Information Retrieval
• C#
• Web Developer
• CTO
• Project Manager

23. 23
How?
GitHub- DiceTechJobs/ConceptualSearch:
1. Pre-Process documents – parse html, strip noise characters, tokenize words
2. Define important keywords for your domain, or use my code to auto extract top
terms and phrases
3. Train Word2Vec model on documents to produce a word2vec model
4. Using this model, either:
1. Vectors: Use the raw vectors and embed them in Solr using synonyms + payloads
2. Top N Similar: Or extract the top n similar terms with similarities and embed these as
weighted synonyms using my custom queryboost parser and tokenizer
3. Clusters: Cluster these vectors by similarity, and map terms to clusters in a synonym file

24. 24
Define Top Domain Specific Keywords
• If you have a set of documents belonging to a specific domain, it is
important to define the important keywords for your domain:
• Use top few thousand search keywords
• Or use my fast keyword and phrase extraction tool (in GitHub)
• Or use SolrLucene shingle filter to extract top 1 - 4 word sequences by
document frequency
• Important to map common phrases to single tokens, e.g. data scientist =>
data_scientist, java developer=>java_developer

25. 25
Do It Yourself
• All code for this talk is now publicly available on GitHub:
• https://github.com/DiceTechJobs/SolrPlugins - Solr plugins to work with
conceptual search, and other dice plugins, such as a custom MLT handler
• https://github.com/DiceTechJobs/SolrConfigExamples - Examples of Solr
configuration file entries to enable conceptual search and other Dice
plugins:
• https://github.com/DiceTechJobs/ConceptualSearch - Python code to
compute the Word2Vec word vectors, and generate Solr synonym files

26. 26
Some Solr Tricks to Make this Happen
1. Keyword Extraction: Use the synonym filter to extract key words from your
documents

27. 27

28. 28
Some Solr Tricks to Make this Happen
1. Keyword Extraction: Use the synonym filter to extract key words from your
documents
2. Synonym Expansion using Payloads:
• Use the synonym filter to expand a keyword to multiple tokens
• Each token has an associated payload – used to adjust relevancy scores at
index or query time

29. 29

30. 30
Synonym File Examples – Vector Method
• Each keyword maps to a set of tokens via a synonym file
• Vector Synonym file entry (5 element vector, usually100+ elements):
• java developer=>001|0.4 002|0.1 003|0.5 005|.9
• Uses a custom token filter that averages these vectors over the entire
document (see GitHub - DiceTechJobs/SolrPlugins)
• Relatively fast at index time but some additional indexing overhead
• Very slow to query

32. 32
Synonym File Examples – Top N Method
• Each keyword maps to a set of most similar keywords via a synonym file
• Top N Synonym file entry (top 5):
• java_developer=>java_j2ee_developer|0.907526 java_architect|0.889903
lead_java_developer|0.867594 j2ee_developer|0.864028 java_engineer|0.861407
• Can configure this at index time with payloads, a payload aware query parser and a
payload similarity function
• Or you can configure this at query time with a special token filter that converts
payloads into term boosts, along with a special parser (see
GitHub - DiceTechJobs/SolrPlugins)
• Fast at index and query time if N is reasonable (10-30)

33. 33
Searching over Clustered Terms
• After we have learned word vectors, we can use a clustering algorithm to
cluster terms by their vectors to give clusters of related words
• Can learn several different sizes of cluster, such as 500, 1000, 5000 clusters,
and map each of these to a separate field
• Apply stronger boosts to the fields containing smaller clusters (e.g. the 5000
cluster field) using the edismax qf parameter - tighter clusters get more
weight
• Code for clustering vectors in GitHub - DiceTechJobs/ConceptualSearch

34. 34
Synonym File Examples – Clustering Method
• Each keyword in a cluster maps the same artificial token for that cluster
• Cluster Synonym file entries:
• java=>cluster_171
• java applications=>cluster_171
• java coding=>cluster_171
• java design=>cluster_171
• Doesn’t use payloads so does not require any special plugins
• No noticeable impact on query or indexing performance

35. 35
Example Clusters Learned from Dice Job Postings
• Note: Labels in bold are manually assigned for interpretability:
• Natural Languages: bi lingual, bilingual, chinese, fluent, french, german, japanese,
korean, lingual, localized, portuguese, russian, spanish, speak, speaker
• Apple Programming Languages: cocoa, swift
• Search Engine Technologies: apache solr, elasticsearch, lucene, lucene solr,
search, search engines, search technologies, solr, solr lucene
• Microsoft .Net Technologies: c# wcf, microsoft c#, microsoft.net, mvc web, wcf
web services, web forms, webforms, windows forms, winforms, wpf wcf

36. 36
Example Clusters Learned from Dice Job Postings
AttentionAttitude:
attention, attentive, close attention, compromising, conscientious, conscious, customer
oriented, customer service focus, customer service oriented, deliver results, delivering results,
demonstrated commitment, dependability, dependable, detailed oriented, diligence,
diligent, do attitude, ethic, excellent follow, extremely detail oriented, good attention,
meticulous, meticulous attention, organized, orientated, outgoing, outstanding customer
service, pay attention, personality, pleasant, positive attitude, professional appearance,
professional attitude, professional demeanor, punctual, punctuality, self motivated, self
motivation, superb, superior, thoroughness

37. 37
Summary
• It’s easy to overlook recall when performing relevancy tuning
• Conceptual search improves recall while maintaining high precision by matching
documents on concepts or ideas.
• In reality this involves learning which terms are related to one another
• Word2Vec is a scalable algorithm for learning related words from a set of documents, that
gives state of the art results in word analogy tasks
• We can train a Word2Vec model offline, and embed it’s output into Solr by using the in-built
synonym filter and payload functionality, combined with some custom plugins