NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics
About
The dominant paradigm for neural text generation is left-to-right decoding from autoregressive language models. Constrained or controllable generation under complex lexical constraints, however, requires foresight to plan ahead feasible future paths. Drawing inspiration from the A* search algorithm, we propose NeuroLogic A*esque, a decoding algorithm that incorporates heuristic estimates of future cost. We develop efficient lookahead heuristics that are efficient for large-scale language models, making our method a drop-in replacement for common techniques such as beam search and top-k sampling. To enable constrained generation, we build on NeuroLogic decoding (Lu et al., 2021), combining its flexibility in incorporating logical constraints with A*esque estimates of future constraint satisfaction. Our approach outperforms competitive baselines on five generation tasks, and achieves new state-of-the-art performance on table-to-text generation, constrained machine translation, and keyword-constrained generation. The improvements are particularly notable on tasks that require complex constraint satisfaction or in few-shot or zero-shot settings. NeuroLogic A*esque illustrates the power of decoding for improving and enabling new capabilities of large-scale language models.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Story Ending Generation | ROCStories (test) | BLEU-134.4 | 43 | |
| Table-to-text generation | E2ENLG (test) | BLEU49.3 | 37 | |
| Commonsense Generation | CommonGen (test) | ROUGE-L44.3 | 31 | |
| Constrained Machine Translation | WMT EN-DE 2017 (test) | BLEU33.7 | 14 | |
| Constrained Question Generation | interrogative question generation (test) | ROUGE43.7 | 6 |