NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints

Understand

Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text.

• While the dominant recipe for conditional text generation has been large-scale pretrained language models that are finetuned on the task-specific training data, such models do not learn to follow the underlying constraints reliably, even when supervised with large amounts of task-specific examples.
• We propose NeuroLogic Decoding, a simple yet effective algorithm that enables neural language models -- supervised or not -- to generate fluent text while satisfying complex lexical constraints.
• Our approach is powerful yet efficient.