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.
翻译:神经文本生成的主要模式是从自动递减语言模型中左向右解码。然而,在复杂的词汇限制下,受约束或可控的生成需要远见卓识才能规划未来可行的道路。从 A* 搜索算法中汲取灵感,我们提出NeuroLogic A*esque,这是一个解码算法,包含对未来成本的超自然估计。我们开发了高效的外表头的超常理论,对大型语言模型来说是有效的,使我们的方法成为对像梁搜索和顶K抽样等通用技术的低调替代。为了让受限制的生成成为可能,我们以NeuroLogic解码(Lu等人,2021年)为基础,将其纳入逻辑限制的制约与对未来约束满意度的A* esque 估计相结合。我们的方法超越了五代任务的竞争基线,并实现了新的桌面-文字生成、受限制的机器翻译和关键语调的生成。在需要复杂的约束性满意度或少发或零发式环境下,我们特别突出的改进。