CPC G06N 3/086 (2013.01) [G06F 16/1794 (2019.01); G06F 16/30 (2019.01); G06F 16/9535 (2019.01); G06F 40/30 (2020.01); G06F 40/58 (2020.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 20/00 (2019.01); G06F 16/00 (2019.01)] | 18 Claims |
1. A method for translating text comprising:
training a neural network system using first meta information associated with a training pair of a source language text and a target language translation, the first meta information indicating a first topic associated with a domain type;
receiving, at the neural network system from a client device, an input text associated with the domain type and second meta information corresponding to the input text, the second meta information indicating a second topic associated with the domain type;
generating, using the neural network system, a translation of the input text based at least in part on the second meta information, wherein the neural network system disambiguates between alternative translations of a word included in the input text based at least in part on the second meta information; and
outputting a translated domain type comprising the translation of the input text for publication.
|