ecommerce_ops · ecommerce · workflow
Delivery Hero improves multilingual search with few-shot LLM translations across 68 countries
Delivery Hero's global search solution spanning 68 countries faced challenges with dialectal variations, transliterations, and spelling errors that traditional machine translation tools could not accurately handle, particularly failing to capture user intent and regional language nuances.
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 · Multilingual query received
A user submits a search query in one of many languages across 68 countries served by the global search solution.
Tools used
GeminiChatGPT-TurboGoogle TranslateDeepLElastic SearchChatGPT
Outcome
LLM-based few-shot translation using Gemini achieved over 90% accuracy for restaurant-related translations, and A/B testing showed positive improvements in user engagement; the translations are now in production for Talabat and Hungerstation.
What failed first
Commercial machine translation tools Google Translate and DeepL generally performed under 80% accuracy on Arabic grocery search queries, failing to capture user intent and context as effectively as LLMs.
Results
Volume86%
Grounding & classification
Source type: technical build writeup
24 fields verified against source quotes.
enterprise searchtranslationknowledge basebuilder submittedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommerceaccuracy improvementcustomer satisfactiontechnical build writeupecommerce opsdata sync enrichment