Amazon patents translation method that fixes drafts using AI edits
This patent describes a system that translates text by first finding a similar, pre-existing translation in a database. It then combines the original text with this draft and uses a machine learning model to correct specific words for accuracy.
In the filing’s own words
Devices and techniques are generally described for machine translation. In various examples, first text in a first spoken language may be received. A first candidate translation of the first text in a second spoken language may be determined based at least in part on the first text from among a candidate pool of non-translated text associated with a first domain. Combined data representing the first text and the first candidate translation may be generated. A first machine learning model may generate second text by modifying at least one word of the first candidate translation. The second text representing a machine translation of the first text may be output.
What exactly they claim (claim 1)
1. A computer-implemented method of language translation, comprising: determining first text comprising at least one word composed in a first spoken language; generating first embedding data representing the first text; selecting second embedding data stored in non-transitory computer-readable memory based on a similarity between the first embedding data and the second embedding data, the second embedding data representing second text comprising at least one word composed in a second spoken language, wherein the second text is a candidate translation of the first text in the second spoken language; generating first combined data by combining the first text and the second text; inputting the first combined data into a transformer model trained to edit the candidate translation in the second text using the first text; generating, by the transformer model using the first combined data, third text by altering at least one word of the second text, wherein the third text is a corrected translation of the first text in the second spoken language; and outputting the third text.
Facts
- Company
- Amazon (Amazon Technologies, Inc.)
- Official title
- Retrieval and edit-based machine translation
- Patent number
- US12743589B1
- Application number
- 17845823
- Filed
- Jun 21, 2022
- Granted
- Sep 22, 2026
- Inventors
- 6
- Claims
- 20
Classified under
G06F 40/47 Physics & computingG06F 40/221 Physics & computingMore from Amazon in AI & software
- Amazon patents system that cites sources for AI answers Sep 29, 2026
- Amazon patents tech to swap words in movies using actor's voice Sep 8, 2026
- Amazon patents ML tool to add graphics to live sports from moving cameras Sep 15, 2026
- Amazon patents shopping assistant that remembers your search filters Oct 6, 2026
- Amazon patents system where AI agents split tasks and talk to each other Oct 20, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.