The Next Generation of AI-Powered Search
Download as PPTX, PDF3 likes366 views
Trey Grainger discusses the next generation of AI-powered search. He covers many techniques used in modern search systems including signals boosting, learning to rank, semantic search, collaborative filtering, personalized search, and neural search. Grainger also discusses using knowledge graphs, domain modeling, multimodal learning, and thought vectors to power conceptual scoring and merged content understanding.
![Watson: “You appeared to [see a good deal] which was quite invisible to
me”
Sherlock: “Not invisible but unnoticed, Watson. You did not know
where to look, and so you missed all that was important.”The Adventures of Sherlock Holmes, ADVENTURE III. A CASE OF IDENTITY, Sir. Oliver](https://image.slidesharecdn.com/e5nusd1erve1uunb42fl-signature-a57b9fb640e32ef5c79d060363acc49ce4061da9e72e8c21a6ddf9c30dc1dc4c-poli-190925204303/85/The-Next-Generation-of-AI-Powered-Search-18-320.jpg)
![Phrase: Vector:
apple juice: [ 1, 5, 0, 0, 0, 4, 4, 3 ]
cappuccino: [ 0, 5, 3, 0, 4, 1, 2, 3 ]
cheese bread sticks: [ 5, 0, 4, 5, 0, 1,
4, 2 ]
cheese pizza: [ 5, 0, 4, 4, 0, 1, 5, 2 ]
cinnamon bread sticks: [ 5, 0, 4, 5, 0, 1, 4, 2 ]
donut: [ 5, 0, 1, 5, 0, 4, 5, 1 ]
green tea: [ 0, 5, 0, 0, 2, 1, 1, 5 ]
latte: [ 0, 5, 4, 0, 4, 1, 3, 3 ]
soda: [ 0, 5, 0, 0, 3, 5, 5, 0 ]
water: [ 0, 5, 0, 0, 0, 0, 0, 5 ]
Ranked Results: Green Tea
0.94 water
0.85 cappuccino
0.80 latte
0.78 apple juice
0.60 soda
… …
0.19 donut
Vector Similarity
Scores:
Vector Similarity (a, b):
a · b = |a| × |b| × cos(θ)
Ranked Results: Cheese
Pizza
0.99 cheese bread sticks
0.91 cinnamon bread sticks
0.89 donut
0.47 latte
0.46 apple juice
… …
0.19 water](https://image.slidesharecdn.com/e5nusd1erve1uunb42fl-signature-a57b9fb640e32ef5c79d060363acc49ce4061da9e72e8c21a6ddf9c30dc1dc4c-poli-190925204303/85/The-Next-Generation-of-AI-Powered-Search-50-320.jpg)
![Sentence
Embeddings:[ 2, 3, 2, 4, 2, 1, 5, 3 ]
[ 5, 3, 2, 3, 4, 0, 3, 4 ]
. . .
Document Embedding:
[ 4, 1, 4, 2, 1, 2, 4, 3 ]
Word Embeddings:
[ 5, 1, 3, 4, 2, 1, 5, 3 ]
[ 4, 1, 3, 0, 1, 1, 4, 2 ]
. . .
Paragraph Embeddings:
[ 5, 1, 4, 1, 0, 2, 4, 0 ]
[ 1, 1, 4, 2, 1, 0, 0, 0 ]
. . .
Thought Vectors](https://image.slidesharecdn.com/e5nusd1erve1uunb42fl-signature-a57b9fb640e32ef5c79d060363acc49ce4061da9e72e8c21a6ddf9c30dc1dc4c-poli-190925204303/85/The-Next-Generation-of-AI-Powered-Search-51-320.jpg)
The Next Generation of AI-Powered Search
- 2. Trey Grainger Chief Algorithms Officer Lucidworks Next Generation of The
- 3. What is ?
- 4. AI? Machine Learning? Data Science? Neural Search? AI-Powered Search? Deep Learning?
- 6. http://aiPoweredSearch.com ... is my new book!
- 7. Keyword Search Knowledge Graph User Intent Personalized Search Semantic Search Domain-aware Matching The Goal of AI-powered Search Content Understanding Domain Understanding Collaborative Recommendations User Understanding
- 8. image credit: SAS Institute, 1998 Definitions, circa 1998
- 13. AI-powered Search Question / Answer Systems Virtual Assistants • Signals Boosting Models • Learning to Rank • Semantic Search • Collaborative Filtering • Personalized Search • Content Clustering • NLP / Entity Resolution • Semantic Knowledge Graphs • Document Classification • etc. • Neural Search • Word Embeddings • Vector Search • Image / Voice Search • etc. • Question / Answer System • Virtual Assistants • Chatbots • Rules-based Relevancy • etc.
- 14. Proudly built with open-source tech at its core: Apache Solr & Apache Spark Personalizes search with applied machine learning Proven on the world’s biggest information systems
- 15. Query Intent (query classification, semantic query parsing, semantic knowledge graphs, concept expansion, automatic query rewrites, clustering, personalization, question/answer systems, virtual assistants) Search Intelligence Spectrum Basic Keyword Search (inverted index, tf-idf, bm25, multilingual text analysis, query formulation, etc.) Taxonomies / Entity Extraction (entity recognition, taxonomies, ontologies, business rules, synonyms, etc.) Automated Relevancy Tuning (Signals boosting, AB testing / multi- armed bandits testing, signals-based back-testing, genetic algorithms, Learning to Rank) Self-learning
- 16. People to People People to Information People to Insights Search + AI=
- 18. Watson: “You appeared to [see a good deal] which was quite invisible to me” Sherlock: “Not invisible but unnoticed, Watson. You did not know where to look, and so you missed all that was important.”The Adventures of Sherlock Holmes, ADVENTURE III. A CASE OF IDENTITY, Sir. Oliver
- 19. Head? Nose? Abstract Concept of Detective with Pipe Specific hypothesis from Experience (leveraging social cue that this is probably a well-known Final Answer + conceptual context
- 22. Ok, Google… Is Agave Nectar good for you?
- 27. How can we help
- 28. = = = =
- 29. Significance of Feedback Loops User Searches User Sees Results User takes an action Users’ actions inform system improvements
- 32. Signal Collection & Processing User Query Results Alonzo ipad doc10, doc22, doc12, … Elena printer doc84, doc2, doc17, … Ming ipad doc10, doc22, doc12, … … … … User Action Document Alonzo click doc22 Elena click doc17 Ming click doc12 Alonzo purchase doc22 Ming click doc22 Ming purchase doc22 Elena click doc2 … … … ipad ⌕ Signal Processing & Machine Learning Learned Relevance Models
- 33. ipad
- 35. ipad
- 39. Still Available through Query Variations Manual Override By Facebook
- 45. Risks Potential Solutions Reinforces Current Biases • Learning to Rank • Use-case-specific Click Models • User-group bias detection • Inject conceptual diversity Subject To Manipulation • Session Filtering • Quality vs. Quantity Signal Weighting • Only Count Explicit Actions Cold Start Problem • Content-based Relevance • Learning to Rank Signals Boosting + Collaborative Filtering
- 46. Knowledge Graphs Domain modeling Multi-modal Learning Merged Content Thought Vectors Conceptual scoring
- 47. Learned Knowledge Graphs Trey Grainger works for Lucidworks. He is speaking at the Activate 2019 conference. #Activate19 (Activate) is being held in Washington, DC September 9-12, 2019. Trey got his masters degree from Georgia Tech. Trey’s Voicemail
- 48. Learned Knowledge Graphs Trey Grainger works for Lucidworks. He is speaking at the Activate 2019 conference. #Activate19 (Activate) is being held in Washington, DC September 9-12, 2019. Trey got his masters degree from Georgia Tech. Trey’s Voicemail
- 50. Phrase: Vector: apple juice: [ 1, 5, 0, 0, 0, 4, 4, 3 ] cappuccino: [ 0, 5, 3, 0, 4, 1, 2, 3 ] cheese bread sticks: [ 5, 0, 4, 5, 0, 1, 4, 2 ] cheese pizza: [ 5, 0, 4, 4, 0, 1, 5, 2 ] cinnamon bread sticks: [ 5, 0, 4, 5, 0, 1, 4, 2 ] donut: [ 5, 0, 1, 5, 0, 4, 5, 1 ] green tea: [ 0, 5, 0, 0, 2, 1, 1, 5 ] latte: [ 0, 5, 4, 0, 4, 1, 3, 3 ] soda: [ 0, 5, 0, 0, 3, 5, 5, 0 ] water: [ 0, 5, 0, 0, 0, 0, 0, 5 ] Ranked Results: Green Tea 0.94 water 0.85 cappuccino 0.80 latte 0.78 apple juice 0.60 soda … … 0.19 donut Vector Similarity Scores: Vector Similarity (a, b): a · b = |a| × |b| × cos(θ) Ranked Results: Cheese Pizza 0.99 cheese bread sticks 0.91 cinnamon bread sticks 0.89 donut 0.47 latte 0.46 apple juice … … 0.19 water
- 51. Sentence Embeddings:[ 2, 3, 2, 4, 2, 1, 5, 3 ] [ 5, 3, 2, 3, 4, 0, 3, 4 ] . . . Document Embedding: [ 4, 1, 4, 2, 1, 2, 4, 3 ] Word Embeddings: [ 5, 1, 3, 4, 2, 1, 5, 3 ] [ 4, 1, 3, 0, 1, 1, 4, 2 ] . . . Paragraph Embeddings: [ 5, 1, 4, 1, 0, 2, 4, 0 ] [ 1, 1, 4, 2, 1, 0, 0, 0 ] . . . Thought Vectors
- 52. Keyword Search Collaborative Recommendations Knowledge Graph User Intent Personalized Search Semantic Search Domain-aware Matching The Goal of AI-powered Search Content Understanding User Understanding Domain Understanding
- 55. Trey Grainger trey@lucidworks.com @treygrainger Other presentations: http://www.treygrainger.com 50% Discount code: mlgrainger http://aiPoweredSearch.com Books: