Back to timeline

Research · September 26, 2016

GNMT: neural translation in Google Translate

On 26 September 2016 Google posted GNMT, a neural translation system with eight LSTM layers in the encoder and eight in the decoder, and on 27 September moved 100 per cent of Chinese-to-English translations in Google Translate to it, about 18 million a day. In human evaluation it reduced errors against the phrase-based statistical system by 60 per cent on average.

Why it matters

Neural translation, until then mostly a research result, went into a product with millions of users and replaced there, for Chinese to English, the phrase-based statistical system Google Translate had launched with ten years earlier, by the post. It took wordpieces, quantisation and TPUs to do it.

In the first version of the preprint: WMT'14 English to French, 38.95 BLEU for a single model; 36 million sentence pairs; the base model trained for about six days on 96 NVIDIA K80 GPUs; TPU decoding 3.4 times faster than CPU. Table 10: on six pairs of 500 sentences from Wikipedia and news, scored 0 to 6, relative improvement from 58 to 87 per cent. Google's post of the same day gives '55%-85%', so two Google documents disagree. The record gives no English-German result: in version 1 it is inconsistent (24.17 in the introduction and for WPM-32K in the table, 24.61 in the text). The authors note that isolated simple sentences were evaluated.

Event record

Event date
September 26, 2016
Timeline date
Event date
Verification
Sources gathered automatically · September 24, 2026
Lines
ID
evt-0699

Version 1 of arXiv:1609.08144 is of 26 September 2016; Google's post on the production launch is of 27 September. Figures are from version 1.

Sources

Related events