Hugging Face's logo
Tumaini Lyimo's picture
6 5

Tumaini Lyimo

lyimo
edsonML's profile picture acvss24's profile picture Nkuku's profile picture
Ā·

AI & ML interests

None yet

Recent Activity

reacted to singhsidhukuldeep's post with šŸ¤Æ 5 days ago
Excited to share insights from Walmart's groundbreaking semantic search system that revolutionizes e-commerce product discovery! The team at Walmart Global Technology(the team that I am a part of šŸ˜¬) has developed a hybrid retrieval system that combines traditional inverted index search with neural embedding-based search to tackle the challenging problem of tail queries in e-commerce. Key Technical Highlights: ā€¢ The system uses a two-tower BERT architecture where one tower processes queries and another processes product information, generating dense vector representations for semantic matching. ā€¢ Product information is enriched by combining titles with key attributes like category, brand, color, and gender using special prefix tokens to help the model distinguish different attribute types. ā€¢ The neural model leverages DistilBERT with 6 layers and projects the 768-dimensional embeddings down to 256 dimensions using a linear layer, achieving optimal performance while reducing storage and computation costs. ā€¢ To improve model training, they implemented innovative negative sampling techniques combining product category matching and token overlap filtering to identify challenging negative examples. Production Implementation Details: ā€¢ The system uses a managed ANN (Approximate Nearest Neighbor) service to enable fast retrieval, achieving 99% recall@20 with just 13ms latency. ā€¢ Query embeddings are cached with preset TTL (Time-To-Live) to reduce latency and costs in production. ā€¢ The model is exported to ONNX format and served in Java, with custom optimizations like fixed input shapes and GPU acceleration using NVIDIA T4 processors. Results: The system showed significant improvements in both offline metrics and live experiments, with: - +2.84% improvement in NDCG@10 for human evaluation - +0.54% lift in Add-to-Cart rates in live A/B testing This is a fantastic example of how modern NLP techniques can be successfully deployed at scale to solve real-world e-
updated a Space about 1 month ago
lyimo/tobacco
updated a Space about 1 month ago
lyimo/downloadmodel
View all activity

Organizations

Badili Innovations's profile picture SEE Africa's profile picture DevData Analytics Limited's profile picture