The development of deep learning software libraries enabled significant progress in the field by allowing users to focus on modeling, while letting the library to take care of the tedious and time-consuming task of optimizing execution for modern hardware accelerators. However, this has benefited only particular types of deep learning models, such as Transformers, whose primitives map easily to the vectorized computation. The models that explicitly account for structured objects, such as trees and segmentations, did not benefit equally because they require custom algorithms that are difficult to implement in a vectorized form. SynJax directly addresses this problem by providing an efficient vectorized implementation of inference algorithms for structured distributions covering alignment, tagging, segmentation, constituency trees and spanning trees. With SynJax we can build large-scale differentiable models that explicitly model structure in the data. The code is available at https://github.com/deepmind/synjax.

翻译：深度学习软件库的发展使得用户能够专注于建模，同时由库来负责为现代硬件加速器优化执行这一繁琐耗时的任务，从而推动了该领域的显著进步。然而，这仅使特定类型的深度学习模型（例如Transformer）受益，因为其原语易于映射到向量化计算。而对于显式考虑结构化对象（如树和分割）的模型，由于需要难以以向量化形式实现的定制算法，所获收益并不均衡。SynJax直接解决了这一问题，为覆盖对齐、标注、分割、成分句法树和生成树的结构化分布的推理算法提供了高效的向量化实现。借助SynJax，我们可以构建能够显式建模数据中结构的大规模可微分模型。代码见https://github.com/deepmind/synjax。