FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947925742> ?p ?o ?g. }

• W2947925742 abstract "In this paper, we aim at tackling a general issue in NLP tasks where some of the negative examples are highly similar to the positive examples, i.e., hard-negative examples. We propose the distant supervision as a regularizer (DSReg) approach to tackle this issue. The original task is converted to a multi-task learning problem, in which distant supervision is used to retrieve hard-negative examples. The obtained hard-negative examples are then used as a regularizer. The original target objective of distinguishing positive examples from negative examples is jointly optimized with the auxiliary task objective of distinguishing softened positive (i.e., hard-negative examples plus positive examples) from easy-negative examples. In the neural context, this can be done by outputting the same representation from the last neural layer to different $softmax$ functions. Using this strategy, we can improve the performance of baseline models in a range of different NLP tasks, including text classification, sequence labeling and reading comprehension." @default.
• W2947925742 created "2019-06-07" @default.
• W2947925742 creator A5012288572 @default.
• W2947925742 creator A5025603106 @default.
• W2947925742 creator A5027254893 @default.
• W2947925742 creator A5074612639 @default.
• W2947925742 creator A5077851706 @default.
• W2947925742 creator A5081449019 @default.
• W2947925742 date "2019-05-28" @default.
• W2947925742 modified "2023-09-27" @default.
• W2947925742 title "DSReg: Using Distant Supervision as a Regularizer" @default.
• W2947925742 cites W1601924930 @default.
• W2947925742 cites W1604644367 @default.
• W2947925742 cites W174427690 @default.
• W2947925742 cites W1793121960 @default.
• W2947925742 cites W1832693441 @default.
• W2947925742 cites W1940872118 @default.
• W2947925742 cites W2004763266 @default.
• W2947925742 cites W2022204871 @default.
• W2947925742 cites W2064675550 @default.
• W2947925742 cites W2101105183 @default.
• W2947925742 cites W2106191791 @default.
• W2947925742 cites W2107598941 @default.
• W2947925742 cites W2116492146 @default.
• W2947925742 cites W2124219775 @default.
• W2947925742 cites W2132679783 @default.
• W2947925742 cites W2147880316 @default.
• W2947925742 cites W2154652894 @default.
• W2947925742 cites W2158899491 @default.
• W2947925742 cites W2250635077 @default.
• W2947925742 cites W2250726251 @default.
• W2947925742 cites W2250966211 @default.
• W2947925742 cites W2251743902 @default.
• W2947925742 cites W2251939518 @default.
• W2947925742 cites W2270414365 @default.
• W2947925742 cites W2440159969 @default.
• W2947925742 cites W2556468274 @default.
• W2947925742 cites W2562979205 @default.
• W2947925742 cites W2739722817 @default.
• W2947925742 cites W2888882903 @default.
• W2947925742 cites W2951815760 @default.
• W2947925742 cites W2962851944 @default.
• W2947925742 cites W2962902328 @default.
• W2947925742 cites W2962906565 @default.
• W2947925742 cites W2963341956 @default.
• W2947925742 cites W2963355640 @default.
• W2947925742 cites W2963403868 @default.
• W2947925742 cites W2963454301 @default.
• W2947925742 cites W2963625095 @default.
• W2947925742 cites W2963842982 @default.
• W2947925742 cites W2963963993 @default.
• W2947925742 hasPublicationYear "2019" @default.
• W2947925742 type Work @default.
• W2947925742 sameAs 2947925742 @default.
• W2947925742 citedByCount "3" @default.
• W2947925742 countsByYear W29479257422019 @default.
• W2947925742 countsByYear W29479257422020 @default.
• W2947925742 countsByYear W29479257422021 @default.
• W2947925742 crossrefType "posted-content" @default.
• W2947925742 hasAuthorship W2947925742A5012288572 @default.
• W2947925742 hasAuthorship W2947925742A5025603106 @default.
• W2947925742 hasAuthorship W2947925742A5027254893 @default.
• W2947925742 hasAuthorship W2947925742A5074612639 @default.
• W2947925742 hasAuthorship W2947925742A5077851706 @default.
• W2947925742 hasAuthorship W2947925742A5081449019 @default.
• W2947925742 hasConcept C111368507 @default.
• W2947925742 hasConcept C119857082 @default.
• W2947925742 hasConcept C12725497 @default.
• W2947925742 hasConcept C127313418 @default.
• W2947925742 hasConcept C151730666 @default.
• W2947925742 hasConcept C154945302 @default.
• W2947925742 hasConcept C159985019 @default.
• W2947925742 hasConcept C162324750 @default.
• W2947925742 hasConcept C17744445 @default.
• W2947925742 hasConcept C187736073 @default.
• W2947925742 hasConcept C188441871 @default.
• W2947925742 hasConcept C192562407 @default.
• W2947925742 hasConcept C199539241 @default.
• W2947925742 hasConcept C204321447 @default.
• W2947925742 hasConcept C204323151 @default.
• W2947925742 hasConcept C2776359362 @default.
• W2947925742 hasConcept C2779343474 @default.
• W2947925742 hasConcept C2780451532 @default.
• W2947925742 hasConcept C41008148 @default.
• W2947925742 hasConcept C50644808 @default.
• W2947925742 hasConcept C86803240 @default.
• W2947925742 hasConcept C94625758 @default.
• W2947925742 hasConceptScore W2947925742C111368507 @default.
• W2947925742 hasConceptScore W2947925742C119857082 @default.
• W2947925742 hasConceptScore W2947925742C12725497 @default.
• W2947925742 hasConceptScore W2947925742C127313418 @default.
• W2947925742 hasConceptScore W2947925742C151730666 @default.
• W2947925742 hasConceptScore W2947925742C154945302 @default.
• W2947925742 hasConceptScore W2947925742C159985019 @default.
• W2947925742 hasConceptScore W2947925742C162324750 @default.
• W2947925742 hasConceptScore W2947925742C17744445 @default.
• W2947925742 hasConceptScore W2947925742C187736073 @default.
• W2947925742 hasConceptScore W2947925742C188441871 @default.
• W2947925742 hasConceptScore W2947925742C192562407 @default.
• W2947925742 hasConceptScore W2947925742C199539241 @default.

• next