swMATH ID: 31805
Software Authors: Alexander M. Rush
Description: Torch-Struct: Deep Structured Prediction Library. 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 http://nlp.seas.harvard.edu/pytorch-struct/
Homepage: http://nlp.seas.harvard.edu/pytorch-struct/
Source Code:  https://github.com/harvardnlp/pytorch-struct
Dependencies: Python
Keywords: Computation and Language; arXiv_cs.CL; Neural and Evolutionary Computing; arXiv_cs.NE; Machine Learning; arXiv_stat.ML; Python
Related Software: pystruct; PyTorch; CRFsuite; Python; SVMstruct; Dyna; TensorFlow; Pyro; CRF++
Cited in: 0 Documents

Standard Articles

1 Publication describing the Software Year
Torch-Struct: Deep Structured Prediction Library
Alexander M. Rush