7. True NegativesFalse Negatives Selected Elements True
Positives False Positives Relevant Elements Precision Recall How
many selected items are relevant? How many selected items are
relevant?
8. BM25 8
9. When it goes wrong Little Black Dress
10. When it goes wrong Red Valentino
11. BCBGMAXZRIA 11
12. Dress
13. Dress Dress Shirt
14. Dress Dress Shirt Shirt Dress
15. What is a good result?
16. Clickthrough Data
17. Crowdsource Relevance
18. Ordinal Light Pink Heels
19. Pairwise Blue Trainers
20. Pairwise Blue Trainers
21. Search Term Example 1.) designer + category hermes sandal
2.) designer + colour + category burberry black boots 3.) designer
+ fabric + category chloe leather top 4.) color + category gray
hoodie 5.) designer + type asos bag What are people actually
searching?
22. DSSM
23. DSSM with 1D convolution and max pooling C-DSSM
24. CSSM Results Search Result Score Download office Excel 0.54
Word office online 0.50 Apartment office hours 0.33 Internation
office berklely 0.27 Microsoft Office Search Result Score Car body
kits 0.70 Auto body parts 0.55 Calculate body fat 0.22 Forceeld
body armour 0.17 Car body shop
25. Computing the results Store hidden layer representation in
postgres Rank by cosine distance Speed up search with ANN Random
projection trees Calculate query representation at run time Docker,
Django-rest, chef, empire, auto-scaling
26. Images?
27. Images Train 8 layer CNN Swap out soft max layer A soft max
layer for each label of interest 60 Million parameters Build robust
learned representations Represents products as a 4096 element
vector