SOTAVerified

Structured Prediction

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 639 papers

TitleStatusHype
Learning Distributions over Permutations and Rankings with Factorized Representations—0
Nested Named Entity Recognition as Single-Pass Sequence Labeling—0
Multi-domain Multilingual Sentiment Analysis in Industry: Predicting Aspect-based Opinion Quadruples—0
Structured Prediction with Abstention via the Lovász Hinge—0
Predicting Through Generation: Why Generation Is Better for Prediction—0
Volume Optimality in Conformal Prediction with Structured Prediction Sets—0
A Fenchel-Young Loss Approach to Data-Driven Inverse Optimization—0
Learning Identifiable Structures Helps Avoid Bias in DNN-based Supervised Causal LearningCode1
Learning Differentiable Surrogate Losses for Structured Prediction—0
Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output GenerationCode1
Show:102550
← PrevPage 1 of 64Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CVAENegative CLL71.8—Unverified