factual
2007 N-gram translation sped up 400,000x
The 2007 Google machine translation system won a DARPA contest by a large BLEU-score margin but took 12 hours per sentence because it did 100,000 disk seeks per word; by designing an in-memory compressed representation of two-trillion-word five-gram data across 200 machines with a batched lookup API, Jeff reduced translation time from roughly a night per sentence to about 100 milliseconds.
factualpending
Speaker
Jeff DeanEvidence Quote
“I built a data structure that would let you store all those in memory on 200 machines and then have sort of a batched API... That enabled us to go from taking a night to translate a sentence to basically doing something in 100 milliseconds”
Created: 6/13/2026, 3:30:41 AM
Your notes
Loading notes...