ecommerce_ops · workflow
Canva builds a CLIP-inspired multilingual deep learning model to suggest keywords for template creators
Newer creators on Canva's marketplace struggled to identify appropriate keywords for their templates, and all keywords needed to work across multiple languages to serve a global user base, while standard classification models could not support an open-ended keyword vocabulary.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Creator template text input
The text content of a creator's template is used as the model input, with keywords as the target output.
Tools used
multilingual sentence transformersCLIPPyTorch
Outcome
The model is currently serving thousands of Canva creators, providing keyword suggestions across multiple languages with support for an effectively unlimited keyword vocabulary.
What failed first
Using binary cross entropy loss (as in standard CLIP training) led to very poor results, because far more negative labels than positive samples caused the loss to focus on pushing vectors apart rather than pulling relevant keywords closer.
Grounding & classification
Source type: technical build writeup
15 fields verified against source quotes.
recommendation systemproduct catalogfailure mode describednamed customerproduction runtime claimedsource backedtools describedworkflow describedsoftwareemployee productivitytechnical build writeupecommerce opsdocument to record