公开(公告)号：US11875141B2

公开(公告)日：2024-01-16

申请号：US17532948

申请日：2021-11-22

Applicant: INFOSYS LIMITED

Inventor： Kamalkumar Rathinasamy ,  Amanpreet Singh ,  Balaguru Sivasambagupta ,  Prajna Prasad Neerchal ,  Vani Sivasankaran

IPC: G06F8/51 ,  G06N3/08 ,  G06F8/41 ,  G06F40/40

CPC classification number: G06F8/51 ,  G06F8/447 ,  G06N3/08 ,  G06F40/40

Abstract: The system and method for training a neural machine translation (NMT) model is disclosed wherein training data in terms of source statements and equivalent targets statements may be received. The source statements and equivalent targets statements may be encoded using source and target vocabulary respectively. A source-target map containing relation between tokens is created. The source statements and equivalent target statements is split into multiple fragments using fragments generator based on the source-target map. Such generated multiple fragments are used to train NMT model. Whenever the trained NMT model receives a source codes as input, the source codes are transformed to target codes.