Haystack 2019 Lightning Talk - Quaerite a Search relevance evaluation toolkit - Tim Allison

OpenSource Connections
OpenSource ConnectionsPrincipal, OpenSource Connections and Solr Consultant at OpenSource Connections
© 2019 The MITRE Corporation. All rights reserved.
Quaerite – Search Relevance Toolkit
Tim Allison
tallison@apache.org, @_tallison
April 24, 2019
Haystack Conference
Approved for Public Release;
Distribution Unlimited. Case
Number 18-3138-5
| 2 |
© 2019 The MITRE Corporation. All rights reserved.
Debt of Gratitude
▪ Thank you Doug Turnbull, John Berryman and Open Source
Connections for the inspiration/examples/training with tmdb and for
sharing your ground truth set!
| 3 |
© 2019 The MITRE Corporation. All rights reserved.
Yet Another Toolkit? Why!?
▪ How many parameters do we have?
▪ How many permutations of those parameters are available?
| 4 |
© 2019 The MITRE Corporation. All rights reserved.
Available Parameters
▪ 14 tokenizers https://lucene.apache.org/solr/guide/7_1/tokenizers.html
▪ ~45 token filters (not including language-specific token filters – see next slide)
https://lucene.apache.org/solr/guide/7_1/filter-descriptions.html
▪ Query parsers
▪ Query operators, minimum should match, should, must, not
▪ Token/field based scoring – best_fields, most_fields, cross_fields
▪ Field boosting
▪ Phrasal boosting/shingling
▪ Synonym lists, taxonomies
▪ Similarity scoring parameters (with BM25)
▪ Elevate
▪ External signal enrichment
– manual or automatic (NLP – entity extraction, categorization, etc.)
▪ Reranking via machine learning (Learning to Rank)
| 4 |
© 2019 The MITRE Corporation. All rights reserved. For internal MITRE use
| 5 |
© 2019 The MITRE Corporation. All rights reserved.
Each Token Filter Can Have Many Parameters
<filter class="solr.WordDelimiterFilterFactory"
protected="protwords.txt"
generateWordParts="1"
generateNumberParts="1"
catenateWords="1"
catenateNumbers="1"
catenateAll="0"
splitOnCaseChange="0"
preserveOriginal="1"/>
| 5 |
© 2019 The MITRE Corporation. All rights reserved. For internal MITRE use
| 6 |
© 2019 The MITRE Corporation. All rights reserved.
Overview – Offline testing toolkit
Prerequisites:
1. Reliable, generalizable ground truth
2. Reliable, useful underlying data
3. Offline metric has to have some connection to KPIs
4. Expertise – you still have to know what you’re doing!!!
| 7 |
© 2019 The MITRE Corporation. All rights reserved.
Main Tools
1. Run Experiments
2. Generate Experiments
▪ All permutations (grid search)
▪ Random experiments (random search)
3. Genetic Algorithm
▪ Cross-fold validation!!!
▪ Complementary to LTR -- main diff is algorithm and in running offline to tune general settings rather
than as reranking top n
| 8 |
© 2019 The MITRE Corporation. All rights reserved.
Odds and Ends
▪ Analyzer Comparison over (mostly) the index
▪ Significant Terms (yawn…for archaic versions of Solr)…and planning to
add these as parameters in “generate experiments”
| 9 |
© 2019 The MITRE Corporation. All rights reserved.
Adding Porter Stemming: create account
creat
created: 709
create: 551
creating: 269
creates: 153
creat: 1
account
account: 3244
accounts: 1924
accounting: 1548
accountants: 340
accountant: 176
accounted: 134
accountability: 74
accountable: 74
accountancy: 65
account's: 7
accountant's: 7
| 10 |
© 2019 The MITRE Corporation. All rights reserved.
Status
▪ Alpha release 3/22/2019 (Solr only)
▪ Beta1 release this week (?)
– This will include support for ElasticSearch
▪ Dream
– Incorporate experiment generation/GA into Rated Ranking Evaluator (RRE)
– Apache Incubator -> Top Level Project (TLP)
| 11 |
© 2019 The MITRE Corporation. All rights reserved.
Links
▪ Main site: https://github.com/mitre/quaerite
▪ Examples: https://github.com/mitre/quaerite/blob/master/quaerite-
examples/README.md
▪ Contact
– tallison@apache.org
– @_tallison
1 of 11

More Related Content

What's hot(20)

Datahive 360 - Felipe WesbonkDatahive 360 - Felipe Wesbonk
Datahive 360 - Felipe Wesbonk
Immelda Oord88 views
Building A Feature FactoryBuilding A Feature Factory
Building A Feature Factory
Databricks1K views
The DataSift platform The DataSift platform
The DataSift platform
ChrisParsons7608 views
Get best data scraperGet best data scraper
Get best data scraper
ApiScrapy AIMLEAP79 views
Esri in AWS CloudEsri in AWS Cloud
Esri in AWS Cloud
Harsh Prakash (AWS, Azure, Security+, Agile, PMP, GISP)5.7K views
SharePoint Search Results BrandingSharePoint Search Results Branding
SharePoint Search Results Branding
Cory Peters676 views
Powering Next Best ActionPowering Next Best Action
Powering Next Best Action
All Things Open174 views
Schema on read with runtime fieldsSchema on read with runtime fields
Schema on read with runtime fields
Elasticsearch5.7K views
Arquitectura de Datos en AzureArquitectura de Datos en Azure
Arquitectura de Datos en Azure
Elena Lopez61 views
Esri ArcGIS FederalEsri ArcGIS Federal
Esri ArcGIS Federal
Harsh Prakash (AWS, Azure, Security+, Agile, PMP, GISP)5.8K views
Esri WebGIS PlatformEsri WebGIS Platform
Esri WebGIS Platform
Harsh Prakash (AWS, Azure, Security+, Agile, PMP, GISP)5K views

Similar to Haystack 2019 Lightning Talk - Quaerite a Search relevance evaluation toolkit - Tim Allison

Similar to Haystack 2019 Lightning Talk - Quaerite a Search relevance evaluation toolkit - Tim Allison(20)

More from OpenSource Connections(20)

EncoresEncores
Encores
OpenSource Connections2K views
Test driven relevancyTest driven relevancy
Test driven relevancy
OpenSource Connections272 views
How To Structure Your Search Team for SuccessHow To Structure Your Search Team for Success
How To Structure Your Search Team for Success
OpenSource Connections162 views
Payloads and OCR with SolrPayloads and OCR with Solr
Payloads and OCR with Solr
OpenSource Connections655 views
Haystack 2019 - Search with Vectors - Simon HughesHaystack 2019 - Search with Vectors - Simon Hughes
Haystack 2019 - Search with Vectors - Simon Hughes
OpenSource Connections1.6K views

Recently uploaded(20)

Building Real-Time Travel AlertsBuilding Real-Time Travel Alerts
Building Real-Time Travel Alerts
Timothy Spann102 views
PTicketInput.pdfPTicketInput.pdf
PTicketInput.pdf
stuartmcphersonflipm314 views
How Leaders See Data? (Level 1)How Leaders See Data? (Level 1)
How Leaders See Data? (Level 1)
Narendra Narendra10 views
Journey of Generative AIJourney of Generative AI
Journey of Generative AI
thomasjvarghese4918 views
RIO GRANDE SUPPLY COMPANY INC, JAYSON.docxRIO GRANDE SUPPLY COMPANY INC, JAYSON.docx
RIO GRANDE SUPPLY COMPANY INC, JAYSON.docx
JaysonGarabilesEspej6 views
Data structure and algorithm. Data structure and algorithm.
Data structure and algorithm.
Abdul salam 12 views
MOSORE_BRESCIAMOSORE_BRESCIA
MOSORE_BRESCIA
Federico Karagulian5 views
3196 The Case of The East River3196 The Case of The East River
3196 The Case of The East River
ErickANDRADE9011 views
Survey on Factuality in LLM's.pptxSurvey on Factuality in LLM's.pptx
Survey on Factuality in LLM's.pptx
NeethaSherra15 views
PROGRAMME.pdfPROGRAMME.pdf
PROGRAMME.pdf
HiNedHaJar14 views
ColonyOSColonyOS
ColonyOS
JohanKristiansson69 views

Haystack 2019 Lightning Talk - Quaerite a Search relevance evaluation toolkit - Tim Allison

  • 1. © 2019 The MITRE Corporation. All rights reserved. Quaerite – Search Relevance Toolkit Tim Allison tallison@apache.org, @_tallison April 24, 2019 Haystack Conference Approved for Public Release; Distribution Unlimited. Case Number 18-3138-5
  • 2. | 2 | © 2019 The MITRE Corporation. All rights reserved. Debt of Gratitude ▪ Thank you Doug Turnbull, John Berryman and Open Source Connections for the inspiration/examples/training with tmdb and for sharing your ground truth set!
  • 3. | 3 | © 2019 The MITRE Corporation. All rights reserved. Yet Another Toolkit? Why!? ▪ How many parameters do we have? ▪ How many permutations of those parameters are available?
  • 4. | 4 | © 2019 The MITRE Corporation. All rights reserved. Available Parameters ▪ 14 tokenizers https://lucene.apache.org/solr/guide/7_1/tokenizers.html ▪ ~45 token filters (not including language-specific token filters – see next slide) https://lucene.apache.org/solr/guide/7_1/filter-descriptions.html ▪ Query parsers ▪ Query operators, minimum should match, should, must, not ▪ Token/field based scoring – best_fields, most_fields, cross_fields ▪ Field boosting ▪ Phrasal boosting/shingling ▪ Synonym lists, taxonomies ▪ Similarity scoring parameters (with BM25) ▪ Elevate ▪ External signal enrichment – manual or automatic (NLP – entity extraction, categorization, etc.) ▪ Reranking via machine learning (Learning to Rank) | 4 | © 2019 The MITRE Corporation. All rights reserved. For internal MITRE use
  • 5. | 5 | © 2019 The MITRE Corporation. All rights reserved. Each Token Filter Can Have Many Parameters <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/> | 5 | © 2019 The MITRE Corporation. All rights reserved. For internal MITRE use
  • 6. | 6 | © 2019 The MITRE Corporation. All rights reserved. Overview – Offline testing toolkit Prerequisites: 1. Reliable, generalizable ground truth 2. Reliable, useful underlying data 3. Offline metric has to have some connection to KPIs 4. Expertise – you still have to know what you’re doing!!!
  • 7. | 7 | © 2019 The MITRE Corporation. All rights reserved. Main Tools 1. Run Experiments 2. Generate Experiments ▪ All permutations (grid search) ▪ Random experiments (random search) 3. Genetic Algorithm ▪ Cross-fold validation!!! ▪ Complementary to LTR -- main diff is algorithm and in running offline to tune general settings rather than as reranking top n
  • 8. | 8 | © 2019 The MITRE Corporation. All rights reserved. Odds and Ends ▪ Analyzer Comparison over (mostly) the index ▪ Significant Terms (yawn…for archaic versions of Solr)…and planning to add these as parameters in “generate experiments”
  • 9. | 9 | © 2019 The MITRE Corporation. All rights reserved. Adding Porter Stemming: create account creat created: 709 create: 551 creating: 269 creates: 153 creat: 1 account account: 3244 accounts: 1924 accounting: 1548 accountants: 340 accountant: 176 accounted: 134 accountability: 74 accountable: 74 accountancy: 65 account's: 7 accountant's: 7
  • 10. | 10 | © 2019 The MITRE Corporation. All rights reserved. Status ▪ Alpha release 3/22/2019 (Solr only) ▪ Beta1 release this week (?) – This will include support for ElasticSearch ▪ Dream – Incorporate experiment generation/GA into Rated Ranking Evaluator (RRE) – Apache Incubator -> Top Level Project (TLP)
  • 11. | 11 | © 2019 The MITRE Corporation. All rights reserved. Links ▪ Main site: https://github.com/mitre/quaerite ▪ Examples: https://github.com/mitre/quaerite/blob/master/quaerite- examples/README.md ▪ Contact – tallison@apache.org – @_tallison