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推动了该领域的显著进步，它允许用户专注于建模，同时由库负责处理在现代硬件加速器上优化执行这一繁琐耗时的任务。然而，这仅使特定类型的深度学习模型（例如Transformer）受益，因为其基本操作易于映射到向量化计算。而明确考虑结构化对象（如树和分割）的模型并未同等受益，因为它们需要难以以向量化形式实现的自定义算法。SynJax直接解决了这一问题，为结构化分布（涵盖对齐、标注、分割、成分树和生成树）提供了高效的向量化推理算法实现。借助SynJax，我们可以构建大规模可微模型，显式地对数据中的结构进行建模。代码可在https://github.com/deepmind/synjax获取。