FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3096710130> ?p ?o ?g. }

• W3096710130 abstract "Abstract Neural network methods which leverage word-embedding obtained from unsupervised learning models have been widely adopted in many natural language processing (NLP) tasks, including sentiment analysis and sentence classification. Existing sentence representation generation approaches which serve for classification tasks generally rely on complex deep neural networks but relatively simple loss functions, such as cross entropy loss function. These approaches cannot produce satisfactory separable sentence representations because the usage of cross entropy may ignore the sentiment and semantic information of the labels. To extract useful information from labels for improving the distinguishability of the obtained sentence representations, this paper proposes a label-oriented loss function. The proposed loss function takes advantage of the word-embeddings of labels to guide the production of meaningful sentence representations which serve for downstream classification tasks. Compared with existing end-to-end approaches, the evaluation experiments on several datasets illustrate that using the proposed loss function can achieve competitive and even better classification results." @default.
• W3096710130 created "2020-11-09" @default.
• W3096710130 creator A5016865114 @default.
• W3096710130 creator A5027336778 @default.
• W3096710130 creator A5064641821 @default.
• W3096710130 creator A5085078586 @default.
• W3096710130 date "2021-03-01" @default.
• W3096710130 modified "2023-10-12" @default.
• W3096710130 title "A label-oriented loss function for learning sentence representations" @default.
• W3096710130 cites W100623710 @default.
• W3096710130 cites W1533946607 @default.
• W3096710130 cites W1550206324 @default.
• W3096710130 cites W179875071 @default.
• W3096710130 cites W1889268436 @default.
• W3096710130 cites W1970689298 @default.
• W3096710130 cites W1985258458 @default.
• W3096710130 cites W2059503205 @default.
• W3096710130 cites W2062522089 @default.
• W3096710130 cites W2064675550 @default.
• W3096710130 cites W2070246124 @default.
• W3096710130 cites W2076094076 @default.
• W3096710130 cites W2091632079 @default.
• W3096710130 cites W2109317801 @default.
• W3096710130 cites W2113459411 @default.
• W3096710130 cites W2115733720 @default.
• W3096710130 cites W2117130368 @default.
• W3096710130 cites W2119408773 @default.
• W3096710130 cites W2121227244 @default.
• W3096710130 cites W2132166724 @default.
• W3096710130 cites W2149684865 @default.
• W3096710130 cites W2154359981 @default.
• W3096710130 cites W2155144632 @default.
• W3096710130 cites W2158899491 @default.
• W3096710130 cites W2160660844 @default.
• W3096710130 cites W2170240176 @default.
• W3096710130 cites W2171061940 @default.
• W3096710130 cites W2250539671 @default.
• W3096710130 cites W2250981850 @default.
• W3096710130 cites W2251939518 @default.
• W3096710130 cites W2402268235 @default.
• W3096710130 cites W2405223529 @default.
• W3096710130 cites W2473555522 @default.
• W3096710130 cites W2511498338 @default.
• W3096710130 cites W2555897561 @default.
• W3096710130 cites W2571563030 @default.
• W3096710130 cites W2605035112 @default.
• W3096710130 cites W2624413595 @default.
• W3096710130 cites W2776249353 @default.
• W3096710130 cites W2787560479 @default.
• W3096710130 cites W2791521493 @default.
• W3096710130 cites W2949547296 @default.
• W3096710130 cites W2949888546 @default.
• W3096710130 cites W2950106848 @default.
• W3096710130 cites W2950133940 @default.
• W3096710130 cites W2950500591 @default.
• W3096710130 cites W2950726992 @default.
• W3096710130 cites W2950910987 @default.
• W3096710130 cites W2951278869 @default.
• W3096710130 cites W2952186591 @default.
• W3096710130 cites W2963918774 @default.
• W3096710130 cites W2964013229 @default.
• W3096710130 cites W2977321685 @default.
• W3096710130 cites W3099206234 @default.
• W3096710130 cites W3142108954 @default.
• W3096710130 doi "https://doi.org/10.1016/j.csl.2020.101165" @default.
• W3096710130 hasPublicationYear "2021" @default.
• W3096710130 type Work @default.
• W3096710130 sameAs 3096710130 @default.
• W3096710130 citedByCount "1" @default.
• W3096710130 countsByYear W30967101302022 @default.
• W3096710130 crossrefType "journal-article" @default.
• W3096710130 hasAuthorship W3096710130A5016865114 @default.
• W3096710130 hasAuthorship W3096710130A5027336778 @default.
• W3096710130 hasAuthorship W3096710130A5064641821 @default.
• W3096710130 hasAuthorship W3096710130A5085078586 @default.
• W3096710130 hasConcept C119857082 @default.
• W3096710130 hasConcept C138885662 @default.
• W3096710130 hasConcept C14036430 @default.
• W3096710130 hasConcept C153083717 @default.
• W3096710130 hasConcept C154945302 @default.
• W3096710130 hasConcept C167981619 @default.
• W3096710130 hasConcept C204321447 @default.
• W3096710130 hasConcept C2777462759 @default.
• W3096710130 hasConcept C2777530160 @default.
• W3096710130 hasConcept C41008148 @default.
• W3096710130 hasConcept C41608201 @default.
• W3096710130 hasConcept C41895202 @default.
• W3096710130 hasConcept C66402592 @default.
• W3096710130 hasConcept C78458016 @default.
• W3096710130 hasConcept C86803240 @default.
• W3096710130 hasConcept C90805587 @default.
• W3096710130 hasConcept C9679016 @default.
• W3096710130 hasConceptScore W3096710130C119857082 @default.
• W3096710130 hasConceptScore W3096710130C138885662 @default.
• W3096710130 hasConceptScore W3096710130C14036430 @default.
• W3096710130 hasConceptScore W3096710130C153083717 @default.
• W3096710130 hasConceptScore W3096710130C154945302 @default.
• W3096710130 hasConceptScore W3096710130C167981619 @default.
• W3096710130 hasConceptScore W3096710130C204321447 @default.
• W3096710130 hasConceptScore W3096710130C2777462759 @default.

• next