Structured Prediction
186 papers with code • 1 benchmarks • 6 datasets
Structured Prediction is an area of machine learning focusing on representations of spaces with combinatorial structure, and algorithms for inference and parameter estimation over these structures. Core methods include both tractable exact approaches like dynamic programming and spanning tree algorithms as well as heuristic techniques such as linear programming relaxations and greedy search.
Libraries
Use these libraries to find Structured Prediction models and implementations
MNIST
ListOps
CFQ
SciREX
WIKIOG
WBM
Most implemented papers
Deep Functional Maps: Structured Prediction for Dense Shape Correspondence
orlitany/DeepFunctionalMaps
•
•
ICCV 2017
We introduce a new framework for learning dense correspondence between deformable 3D shapes.
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
uclanlp/reducingbias
•
•
EMNLP 2017
Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web.
SparseMAP: Differentiable Sparse Structured Inference
Structured prediction requires searching over a combinatorial number of structures.
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
aalmah/augmented_cyclegan
•
•
ICML 2018
Learning inter-domain mappings from unpaired data can improve performance in structured prediction tasks, such as image segmentation, by reducing the need for paired data.
Learning Approximate Inference Networks for Structured Prediction
Prior work used gradient descent for inference, relaxing the structured output to a set of continuous variables and then optimizing the energy with respect to them.
Learning with Fenchel-Young Losses
deep-spin/entmax
•
•
Over the past decades, numerous loss functions have been been proposed for a variety of supervised learning tasks, including regression, classification, ranking, and more generally structured prediction.
The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding
We present MT-DNN, an open-source natural language understanding (NLU) toolkit that makes it easy for researchers and developers to train customized deep learning models.
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
However, many tasks of practical interest have different modalities, such as tabular data, audio, text, or sensor data, which offer significant challenges involving regression and discrete or continuous structured prediction.
ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
Moreover, ReNet layers are stacked on top of pre-trained convolutional layers, benefiting from generic local features.
A Probabilistic Generative Grammar for Semantic Parsing
The work relies on a novel application of hierarchical Dirichlet processes (HDPs) for structured prediction, which we also present in this manuscript.
