论文标题
火炬结构：深层结构化预测库
Torch-Struct: Deep Structured Prediction Library
论文作者
论文摘要
NLP结构化预测的文献描述了序列，分割，比对和树的丰富分布和算法集合；但是，这些算法很难在深度学习框架中使用。我们介绍了Torch结构，这是一个用于结构化预测的库，旨在利用并集成到基于自动差异的框架的框架。火炬结构包括通过简单且灵活的基于分布的API访问的大量概率结构，该结构连接到任何深度学习模型。该库利用批处理，矢量化操作和利用自动差异来生成可读，快速和可测试的代码。在内部，我们还包括许多通用优化，以提供交叉呈叠加效率。实验表明，对快速基线的表现显着增长，案例研究表明了图书馆的好处。火炬结构可在https://github.com/harvardnlp/pytorch-scruct上找到。
The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning frameworks. We introduce Torch-Struct, a library for structured prediction designed to take advantage of and integrate with vectorized, auto-differentiation based frameworks. Torch-Struct includes a broad collection of probabilistic structures accessed through a simple and flexible distribution-based API that connects to any deep learning model. The library utilizes batched, vectorized operations and exploits auto-differentiation to produce readable, fast, and testable code. Internally, we also include a number of general-purpose optimizations to provide cross-algorithm efficiency. Experiments show significant performance gains over fast baselines and case-studies demonstrate the benefits of the library. Torch-Struct is available at https://github.com/harvardnlp/pytorch-struct.
