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 471–480 of 639 papers

TitleStatusHype
Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss—0
On Regularization and Inference with Label Constraints—0
On the definition of a general learning system with user-defined operators—0
On the Discrepancy between Density Estimation and Sequence Generation—0
Duality in RKHSs with Infinite Dimensional Outputs: Application to Robust Losses—0
On the Fundamental Limits of Exact Inference in Structured Prediction—0
On the inconsistency of separable losses for structured prediction—0
Optimality of Approximate Inference Algorithms on Stable Instances—0
Optimization Strategies for Online Large-Margin Learning in Machine Translation—0
Optimizing for Measure of Performance in Max-Margin Parsing—0
Show:102550
← PrevPage 48 of 64Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CVAENegative CLL71.8—Unverified