Structured Prediction

138 papers with code • 1 benchmarks • 5 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.

Source: Torch-Struct: Deep Structured Prediction Library

Greatest papers with code

The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables

tensorflow/models 2 Nov 2016

The essence of the trick is to refactor each stochastic node into a differentiable function of its parameters and a random variable with fixed distribution.

Density Estimation Structured Prediction

Classical Structured Prediction Losses for Sequence to Sequence Learning

pytorch/fairseq NAACL 2018

There has been much recent work on training neural attention models at the sequence-level using either reinforcement learning-style methods or by optimizing the beam.

Abstractive Text Summarization Machine Translation +2

On the Discrepancy between Density Estimation and Sequence Generation

tensorflow/tensor2tensor EMNLP (spnlp) 2020

In this paper, by comparing several density estimators on five machine translation tasks, we find that the correlation between rankings of models based on log-likelihood and BLEU varies significantly depending on the range of the model families being compared.

Density Estimation Latent Variable Models +3

The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models

PAIR-code/lit EMNLP 2020

We present the Language Interpretability Tool (LIT), an open-source platform for visualization and understanding of NLP models.

Sentiment Analysis Structured Prediction +1

The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding

namisan/mt-dnn ACL 2020

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.

Knowledge Distillation Language understanding +3

Torch-Struct: Deep Structured Prediction Library

harvardnlp/pytorch-struct ACL 2020

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.

Structured Prediction

Torch-Struct: Deep Structured Prediction Library

harvardnlp/pytorch-struct ACL 2020

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.

Structured Prediction

A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning

TorchCraft/TorchCraftAI NeurIPS 2019

While centralized reinforcement learning methods can optimally solve small MAC instances, they do not scale to large problems and they fail to generalize to scenarios different from those seen during training.

Multi-agent Reinforcement Learning Starcraft +1