Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037970480> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3037970480 endingPage "1268" @default.
- W3037970480 startingPage "1258" @default.
- W3037970480 abstract "Existing disambiguation strategies for partial structured output learning just cannot generalize well to solve the problem that there are some candidates that can be false positive or similar to the ground-truth label. In this article, we propose a novel weak disambiguation for partial structured output learning (WD-PSL). First, a piecewise large margin formulation is generalized to partial structured output learning, which effectively avoids handling a large number of candidate-structured outputs for complex structures. Second, in the proposed weak disambiguation strategy, each candidate label is assigned with a confidence value indicating how likely it is the true label, which aims to reduce the negative effects of wrong ground-truth label assignment in the learning process. Then, two large margins are formulated to combine two types of constraints which are the disambiguation between candidates and noncandidates, and the weak disambiguation for candidates. In the framework of alternating optimization, a new 2n -slack variables cutting plane algorithm is developed to accelerate each iteration of optimization. The experimental results on several sequence labeling tasks of natural language processing show the effectiveness of the proposed model." @default.
- W3037970480 created "2020-07-02" @default.
- W3037970480 creator A5048386675 @default.
- W3037970480 creator A5050716572 @default.
- W3037970480 date "2022-02-01" @default.
- W3037970480 modified "2023-10-16" @default.
- W3037970480 title "Weak Disambiguation for Partial Structured Output Learning" @default.
- W3037970480 cites W1964965834 @default.
- W3037970480 cites W1986916218 @default.
- W3037970480 cites W2024328138 @default.
- W3037970480 cites W2031248101 @default.
- W3037970480 cites W2074521846 @default.
- W3037970480 cites W2137450504 @default.
- W3037970480 cites W2150969560 @default.
- W3037970480 cites W2153603270 @default.
- W3037970480 cites W2161044106 @default.
- W3037970480 cites W2171805028 @default.
- W3037970480 cites W2295800284 @default.
- W3037970480 cites W2429914308 @default.
- W3037970480 cites W2528451364 @default.
- W3037970480 cites W2733555913 @default.
- W3037970480 cites W2799301563 @default.
- W3037970480 cites W2808448059 @default.
- W3037970480 cites W4252331534 @default.
- W3037970480 cites W61442668 @default.
- W3037970480 doi "https://doi.org/10.1109/tcyb.2020.3000053" @default.
- W3037970480 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32574146" @default.
- W3037970480 hasPublicationYear "2022" @default.
- W3037970480 type Work @default.
- W3037970480 sameAs 3037970480 @default.
- W3037970480 citedByCount "0" @default.
- W3037970480 crossrefType "journal-article" @default.
- W3037970480 hasAuthorship W3037970480A5048386675 @default.
- W3037970480 hasAuthorship W3037970480A5050716572 @default.
- W3037970480 hasBestOaLocation W30379704802 @default.
- W3037970480 hasConcept C111919701 @default.
- W3037970480 hasConcept C11413529 @default.
- W3037970480 hasConcept C119857082 @default.
- W3037970480 hasConcept C134306372 @default.
- W3037970480 hasConcept C146849305 @default.
- W3037970480 hasConcept C154945302 @default.
- W3037970480 hasConcept C164660894 @default.
- W3037970480 hasConcept C22367795 @default.
- W3037970480 hasConcept C2776291640 @default.
- W3037970480 hasConcept C2778112365 @default.
- W3037970480 hasConcept C33923547 @default.
- W3037970480 hasConcept C41008148 @default.
- W3037970480 hasConcept C54355233 @default.
- W3037970480 hasConcept C774472 @default.
- W3037970480 hasConcept C86803240 @default.
- W3037970480 hasConcept C98045186 @default.
- W3037970480 hasConceptScore W3037970480C111919701 @default.
- W3037970480 hasConceptScore W3037970480C11413529 @default.
- W3037970480 hasConceptScore W3037970480C119857082 @default.
- W3037970480 hasConceptScore W3037970480C134306372 @default.
- W3037970480 hasConceptScore W3037970480C146849305 @default.
- W3037970480 hasConceptScore W3037970480C154945302 @default.
- W3037970480 hasConceptScore W3037970480C164660894 @default.
- W3037970480 hasConceptScore W3037970480C22367795 @default.
- W3037970480 hasConceptScore W3037970480C2776291640 @default.
- W3037970480 hasConceptScore W3037970480C2778112365 @default.
- W3037970480 hasConceptScore W3037970480C33923547 @default.
- W3037970480 hasConceptScore W3037970480C41008148 @default.
- W3037970480 hasConceptScore W3037970480C54355233 @default.
- W3037970480 hasConceptScore W3037970480C774472 @default.
- W3037970480 hasConceptScore W3037970480C86803240 @default.
- W3037970480 hasConceptScore W3037970480C98045186 @default.
- W3037970480 hasFunder F4320309893 @default.
- W3037970480 hasIssue "2" @default.
- W3037970480 hasLocation W30379704801 @default.
- W3037970480 hasLocation W30379704802 @default.
- W3037970480 hasLocation W30379704803 @default.
- W3037970480 hasOpenAccess W3037970480 @default.
- W3037970480 hasPrimaryLocation W30379704801 @default.
- W3037970480 hasRelatedWork W2095758845 @default.
- W3037970480 hasRelatedWork W2905260191 @default.
- W3037970480 hasRelatedWork W2953238046 @default.
- W3037970480 hasRelatedWork W2955246348 @default.
- W3037970480 hasRelatedWork W3004251094 @default.
- W3037970480 hasRelatedWork W3034077005 @default.
- W3037970480 hasRelatedWork W3037970480 @default.
- W3037970480 hasRelatedWork W3129604848 @default.
- W3037970480 hasRelatedWork W4300631627 @default.
- W3037970480 hasRelatedWork W2998213596 @default.
- W3037970480 hasVolume "52" @default.
- W3037970480 isParatext "false" @default.
- W3037970480 isRetracted "false" @default.
- W3037970480 magId "3037970480" @default.
- W3037970480 workType "article" @default.