Invention Application
- Patent Title: CONDITIONING AUTOREGRESSIVE LANGUAGE MODEL TO IMPROVE CODE MIGRATION
-
Application No.: US17945376Application Date: 2022-09-15
-
Publication No.: US20230018088A1Publication Date: 2023-01-19
- Inventor: Rishabh Singh , David Andre , Bin Ni , Owen Lewis
- Applicant: X Development LLC
- Applicant Address: US CA Mountain View
- Assignee: X Development LLC
- Current Assignee: X Development LLC
- Current Assignee Address: US CA Mountain View
- Main IPC: G06F8/71
- IPC: G06F8/71 ; G06F40/20 ; G06N20/00

Abstract:
Implementations are described herein for using machine learning to perform various tasks related to migrating source code based on relatively few (“few shots”) demonstrations. In various implementations, an autoregressive language model may be conditioned based on demonstration tuple(s). In some implementations, a demonstration tuple may include a pre-migration version of a first source code snippet and a post-migration version of the first source code snippet. In other implementations, demonstration tuples may include other data, such as intermediate forms (e.g., natural language descriptions or pseudocode), input-output pairs demonstrating intended behavior, etc. The autoregressive language model may be trained on corpora of source code and natural language documentation on the subject of computer programming. A pre-migration version of a source code file may be processed based on the conditioned autoregressive language model, and a post-migration version may be generated based on output generated based on the conditioned autoregressive model.
Public/Granted literature
- US11656867B2 Conditioning autoregressive language model to improve code migration Public/Granted day:2023-05-23
Information query