FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100609281> ?p ?o ?g. }

• W3100609281 abstract "The success of deep learning methods hinges on the availability of large training datasets annotated for the task of interest. In contrast to human intelligence, these methods lack versatility and struggle to learn and adapt quickly to new tasks, where labeled data is scarce. Meta-learning aims to solve this problem by training a model on a large number of few-shot tasks, with an objective to learn new tasks quickly from a small number of examples. In this paper, we propose a meta-learning framework for few-shot word sense disambiguation (WSD), where the goal is to learn to disambiguate unseen words from only a few labeled instances. Meta-learning approaches have so far been typically tested in an N-way, K-shot classification setting where each task has N classes with K examples per class. Owing to its nature, WSD deviates from this controlled setup and requires the models to handle a large number of highly unbalanced classes. We extend several popular meta-learning approaches to this scenario, and analyze their strengths and weaknesses in this new challenging setting." @default.
• W3100609281 created "2020-11-23" @default.
• W3100609281 creator A5002745343 @default.
• W3100609281 creator A5016184654 @default.
• W3100609281 creator A5049982208 @default.
• W3100609281 creator A5083950817 @default.
• W3100609281 date "2020-01-01" @default.
• W3100609281 modified "2023-09-23" @default.
• W3100609281 title "Learning to Learn to Disambiguate: Meta-Learning for Few-Shot Word Sense Disambiguation" @default.
• W3100609281 cites W1840435438 @default.
• W3100609281 cites W1971220772 @default.
• W3100609281 cites W1976252502 @default.
• W3100609281 cites W2035717317 @default.
• W3100609281 cites W2064675550 @default.
• W3100609281 cites W2101293500 @default.
• W3100609281 cites W2123399796 @default.
• W3100609281 cites W2127289991 @default.
• W3100609281 cites W2139183784 @default.
• W3100609281 cites W2148125485 @default.
• W3100609281 cites W2157331557 @default.
• W3100609281 cites W2159719802 @default.
• W3100609281 cites W2187089797 @default.
• W3100609281 cites W2194321275 @default.
• W3100609281 cites W2250539671 @default.
• W3100609281 cites W2293111794 @default.
• W3100609281 cites W2436001372 @default.
• W3100609281 cites W2507974895 @default.
• W3100609281 cites W2518202280 @default.
• W3100609281 cites W2550182557 @default.
• W3100609281 cites W2550186622 @default.
• W3100609281 cites W2601450892 @default.
• W3100609281 cites W2604763608 @default.
• W3100609281 cites W2740782137 @default.
• W3100609281 cites W2753160622 @default.
• W3100609281 cites W2757205734 @default.
• W3100609281 cites W2795900505 @default.
• W3100609281 cites W2911681509 @default.
• W3100609281 cites W2921156067 @default.
• W3100609281 cites W2948974578 @default.
• W3100609281 cites W2951465421 @default.
• W3100609281 cites W2953111196 @default.
• W3100609281 cites W2962739339 @default.
• W3100609281 cites W2963310665 @default.
• W3100609281 cites W2963341924 @default.
• W3100609281 cites W2963341956 @default.
• W3100609281 cites W2963403868 @default.
• W3100609281 cites W2963606136 @default.
• W3100609281 cites W2964105864 @default.
• W3100609281 cites W2964121744 @default.
• W3100609281 cites W2964189868 @default.
• W3100609281 cites W2964316912 @default.
• W3100609281 cites W2970166416 @default.
• W3100609281 cites W2970678056 @default.
• W3100609281 cites W2970773744 @default.
• W3100609281 cites W2970971561 @default.
• W3100609281 cites W2971013448 @default.
• W3100609281 cites W2971048662 @default.
• W3100609281 cites W2971167006 @default.
• W3100609281 cites W2971330564 @default.
• W3100609281 cites W2978409868 @default.
• W3100609281 cites W2994676517 @default.
• W3100609281 cites W2995196103 @default.
• W3100609281 cites W3034617042 @default.
• W3100609281 cites W3034782826 @default.
• W3100609281 cites W3091905774 @default.
• W3100609281 cites W3113529090 @default.
• W3100609281 cites W99485931 @default.
• W3100609281 cites W1614862348 @default.
• W3100609281 doi "https://doi.org/10.18653/v1/2020.findings-emnlp.405" @default.
• W3100609281 hasPublicationYear "2020" @default.
• W3100609281 type Work @default.
• W3100609281 sameAs 3100609281 @default.
• W3100609281 citedByCount "15" @default.
• W3100609281 countsByYear W31006092812020 @default.
• W3100609281 countsByYear W31006092812021 @default.
• W3100609281 countsByYear W31006092812022 @default.
• W3100609281 countsByYear W31006092812023 @default.
• W3100609281 crossrefType "proceedings-article" @default.
• W3100609281 hasAuthorship W3100609281A5002745343 @default.
• W3100609281 hasAuthorship W3100609281A5016184654 @default.
• W3100609281 hasAuthorship W3100609281A5049982208 @default.
• W3100609281 hasAuthorship W3100609281A5083950817 @default.
• W3100609281 hasBestOaLocation W31006092811 @default.
• W3100609281 hasConcept C111472728 @default.
• W3100609281 hasConcept C119857082 @default.
• W3100609281 hasConcept C138885662 @default.
• W3100609281 hasConcept C154945302 @default.
• W3100609281 hasConcept C157659113 @default.
• W3100609281 hasConcept C162324750 @default.
• W3100609281 hasConcept C187736073 @default.
• W3100609281 hasConcept C204321447 @default.
• W3100609281 hasConcept C2776502983 @default.
• W3100609281 hasConcept C2777212361 @default.
• W3100609281 hasConcept C2780451532 @default.
• W3100609281 hasConcept C2781002164 @default.
• W3100609281 hasConcept C41008148 @default.
• W3100609281 hasConcept C41895202 @default.
• W3100609281 hasConcept C51646954 @default.
• W3100609281 hasConcept C63882131 @default.
• W3100609281 hasConcept C90805587 @default.

• next