We propose Beam Tree Recursive Cell (BT-Cell) - a backpropagation-friendly framework to extend Recursive Neural Networks (RvNNs) with beam search for latent structure induction. We further extend this framework by proposing a relaxation of the hard top-k operators in beam search for better propagation of gradient signals. We evaluate our proposed models in different out-of-distribution splits in both synthetic and realistic data. Our experiments show that BTCell achieves near-perfect performance on several challenging structure-sensitive synthetic tasks like ListOps and logical inference while maintaining comparable performance in realistic data against other RvNN-based models. Additionally, we identify a previously unknown failure case for neural models in generalization to unseen number of arguments in ListOps. The code is available at: https://github.com/JRC1995/BeamTreeRecursiveCells.

翻译：我们提出束树递归单元（BT-Cell）——一种支持反向传播的框架，用于通过束搜索扩展递归神经网络（RvNNs）以进行潜在结构归纳。我们进一步扩展该框架，提出对束搜索中硬性top-k算子的松弛处理，以改善梯度信号的传播。我们在合成数据和真实数据的不同分布外分割场景中评估了所提出的模型。实验表明，BT-Cell在ListOps和逻辑推理等多个具有挑战性的结构敏感性合成任务上实现了近乎完美的性能，同时在真实数据上与其他基于RvNN的模型保持了相当的表现。此外，我们发现了神经网络模型在ListOps任务中面对未见参数数量时泛化能力的一个此前未知的失效案例。代码开源地址：https://github.com/JRC1995/BeamTreeRecursiveCells。