When we discuss Google's input in NLP, the most important contribution is certainly the "Attention is all you Need" paper, which paved the way for BERT and GTP (Alphafold also uses Attention networks, btw)
Which is the same thing as hand-engineered feature stacks being left behind in vision problems, really. The story in every field is more or less "you're not clever enough to engineer good features"; "you might be clever enough to define good symmetries for the feature space in which the features live... maybe" (convolutional neural networks in image problems); "... but maybe not even that" (attention mechanisms).
People were doing a mix of learning from data and hand engineered solutions before this, but this was the first system learned end-to-end, afaik.
Speaking of which, Google Translate was published in 2006, but when did the "learning from data" approach became an accepted idea in machine translation? I think the earlier attempts at machine translation were more about trying to codify grammar rules in software, than doing statistical learning from large text corpuses? I remember in 2002, the approach of leaning protein substructures from data was already the best performing approach in the protein folding problem.