FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3095514862> ?p ?o ?g. }

• W3095514862 abstract "One critical issue of zero anaphora resolution (ZAR) is the scarcity of labeled data. This study explores how effectively this problem can be alleviated by data augmentation. We adopt a state-of-the-art data augmentation method, called the contextual data augmentation (CDA), that generates labeled training instances using a pretrained language model. The CDA has been reported to work well for several other natural language processing tasks, including text classification and machine translation. This study addresses two underexplored issues on CDA, that is, how to reduce the computational cost of data augmentation and how to ensure the quality of the generated data. We also propose two methods to adapt CDA to ZAR: [MASK]-based augmentation and linguistically-controlled masking. Consequently, the experimental results on Japanese ZAR show that our methods contribute to both the accuracy gain and the computation cost reduction. Our closer analysis reveals that the proposed method can improve the quality of the augmented training data when compared to the conventional CDA." @default.
• W3095514862 created "2020-11-09" @default.
• W3095514862 creator A5000571928 @default.
• W3095514862 creator A5060910700 @default.
• W3095514862 creator A5062386124 @default.
• W3095514862 creator A5066002127 @default.
• W3095514862 creator A5079050003 @default.
• W3095514862 creator A5088188827 @default.
• W3095514862 date "2020-11-02" @default.
• W3095514862 modified "2023-10-05" @default.
• W3095514862 title "An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution" @default.
• W3095514862 cites W116192430 @default.
• W3095514862 cites W1510598116 @default.
• W3095514862 cites W1982477054 @default.
• W3095514862 cites W1985051099 @default.
• W3095514862 cites W2021692535 @default.
• W3095514862 cites W2038245978 @default.
• W3095514862 cites W2039813897 @default.
• W3095514862 cites W204341599 @default.
• W3095514862 cites W2077810047 @default.
• W3095514862 cites W2122346240 @default.
• W3095514862 cites W2123024554 @default.
• W3095514862 cites W2133258739 @default.
• W3095514862 cites W2157331557 @default.
• W3095514862 cites W2158831095 @default.
• W3095514862 cites W2168036300 @default.
• W3095514862 cites W2194775991 @default.
• W3095514862 cites W2196463948 @default.
• W3095514862 cites W2251357896 @default.
• W3095514862 cites W2251599843 @default.
• W3095514862 cites W2251658415 @default.
• W3095514862 cites W2251784867 @default.
• W3095514862 cites W2252071042 @default.
• W3095514862 cites W2508339903 @default.
• W3095514862 cites W2512290434 @default.
• W3095514862 cites W2566130182 @default.
• W3095514862 cites W2626574723 @default.
• W3095514862 cites W2740295529 @default.
• W3095514862 cites W2785611020 @default.
• W3095514862 cites W2786273134 @default.
• W3095514862 cites W2798921788 @default.
• W3095514862 cites W2874600858 @default.
• W3095514862 cites W2905266130 @default.
• W3095514862 cites W2932008548 @default.
• W3095514862 cites W2946068894 @default.
• W3095514862 cites W2953173959 @default.
• W3095514862 cites W2962739339 @default.
• W3095514862 cites W2963011474 @default.
• W3095514862 cites W2963012544 @default.
• W3095514862 cites W2963341956 @default.
• W3095514862 cites W2963545917 @default.
• W3095514862 cites W2963907530 @default.
• W3095514862 cites W2963964835 @default.
• W3095514862 cites W2964121744 @default.
• W3095514862 cites W2970529259 @default.
• W3095514862 cites W3004368295 @default.
• W3095514862 cites W3088059392 @default.
• W3095514862 cites W3088472361 @default.
• W3095514862 cites W3102685326 @default.
• W3095514862 cites W2798956534 @default.
• W3095514862 doi "https://doi.org/10.48550/arxiv.2011.00948" @default.
• W3095514862 hasPublicationYear "2020" @default.
• W3095514862 type Work @default.
• W3095514862 sameAs 3095514862 @default.
• W3095514862 citedByCount "1" @default.
• W3095514862 countsByYear W30955148622021 @default.
• W3095514862 crossrefType "posted-content" @default.
• W3095514862 hasAuthorship W3095514862A5000571928 @default.
• W3095514862 hasAuthorship W3095514862A5060910700 @default.
• W3095514862 hasAuthorship W3095514862A5062386124 @default.
• W3095514862 hasAuthorship W3095514862A5066002127 @default.
• W3095514862 hasAuthorship W3095514862A5079050003 @default.
• W3095514862 hasAuthorship W3095514862A5088188827 @default.
• W3095514862 hasBestOaLocation W30955148621 @default.
• W3095514862 hasConcept C111472728 @default.
• W3095514862 hasConcept C11413529 @default.
• W3095514862 hasConcept C119857082 @default.
• W3095514862 hasConcept C138268822 @default.
• W3095514862 hasConcept C138885662 @default.
• W3095514862 hasConcept C142362112 @default.
• W3095514862 hasConcept C153349607 @default.
• W3095514862 hasConcept C154945302 @default.
• W3095514862 hasConcept C203005215 @default.
• W3095514862 hasConcept C204321447 @default.
• W3095514862 hasConcept C2777402240 @default.
• W3095514862 hasConcept C2779530757 @default.
• W3095514862 hasConcept C2781449363 @default.
• W3095514862 hasConcept C41008148 @default.
• W3095514862 hasConcept C45374587 @default.
• W3095514862 hasConceptScore W3095514862C111472728 @default.
• W3095514862 hasConceptScore W3095514862C11413529 @default.
• W3095514862 hasConceptScore W3095514862C119857082 @default.
• W3095514862 hasConceptScore W3095514862C138268822 @default.
• W3095514862 hasConceptScore W3095514862C138885662 @default.
• W3095514862 hasConceptScore W3095514862C142362112 @default.
• W3095514862 hasConceptScore W3095514862C153349607 @default.
• W3095514862 hasConceptScore W3095514862C154945302 @default.
• W3095514862 hasConceptScore W3095514862C203005215 @default.
• W3095514862 hasConceptScore W3095514862C204321447 @default.
• W3095514862 hasConceptScore W3095514862C2777402240 @default.

• next