Torch-Struct: Deep Structured Prediction Library

02/03/2020
by   Alexander M. Rush, et al.
48

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.

READ FULL TEXT

page 1

page 3

page 4

research
09/10/2018

Torchbearer: A Model Fitting Library for PyTorch

We introduce torchbearer, a model fitting library for pytorch aimed at r...
research
08/07/2023

SynJax: Structured Probability Distributions for JAX

The development of deep learning software libraries enabled significant ...
research
07/10/2018

DLOPT: Deep Learning Optimization Library

Deep learning hyper-parameter optimization is a tough task. Finding an a...
research
10/03/2022

NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning

Imposing explicit constraints is relatively new but increasingly pressin...
research
04/20/2019

DeepMoD: Deep learning for Model Discovery in noisy data

We introduce DeepMoD, a deep learning based model discovery algorithm wh...
research
09/23/2015

IllinoisSL: A JAVA Library for Structured Prediction

IllinoisSL is a Java library for learning structured prediction models. ...
research
03/24/2022

minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models

We present minicons, an open source library that provides a standard API...

Please sign up or login with your details

Forgot password? Click here to reset