Workshop paper
Towards Automating the AI Operations Lifecycle
Matthew Arnold, Jeffrey Boston, et al.
MLSys 2020
We propose an NL paradigm and platform for the construction of business automation rules that incorporate a constrained natural language (CNL) – a domain-specific highly consumable language to validate and review synthesized code. Our approach utilizes LLMs to translate business rules described in NL into CNL for human review which can then be transpiled into the business automation code of the rule engine. To address challenges in the translation from NL to CNL, we utilize several techniques such as constrained decoding, fine-tuning and prompt engineering.
Matthew Arnold, Jeffrey Boston, et al.
MLSys 2020
Shivashankar Subramanian, Ioana Baldini, et al.
IAAI 2020
Chih-kai Ting, Karl Munson, et al.
AAAI 2023
Kevin Gu, Eva Tuecke, et al.
ICML 2024