FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2853138162> ?p ?o ?g. }

• W2853138162 endingPage "1661" @default.
• W2853138162 startingPage "1650" @default.
• W2853138162 abstract "Distributed word embeddings have shown superior performances in numerous Natural Language Processing (NLP) tasks. However, their performances vary significantly across different tasks, implying that the word embeddings learnt by those methods capture complementary aspects of lexical semantics. Therefore, we believe that it is important to combine the existing word embeddings to produce more accurate and complete meta-embeddings of words. We model the meta-embedding learning problem as an autoencoding problem, where we would like to learn a meta-embedding space that can accurately reconstruct all source embeddings simultaneously. Thereby, the meta-embedding space is enforced to capture complementary information in different source embeddings via a coherent common embedding space. We propose three flavours of autoencoded meta-embeddings motivated by different requirements that must be satisfied by a meta-embedding. Our experimental results on a series of benchmark evaluations show that the proposed autoencoded meta-embeddings outperform the existing state-of-the-art meta-embeddings in multiple tasks." @default.
• W2853138162 created "2018-07-19" @default.
• W2853138162 creator A5073503574 @default.
• W2853138162 creator A5076649449 @default.
• W2853138162 date "2018-08-01" @default.
• W2853138162 modified "2023-09-23" @default.
• W2853138162 title "Learning Word Meta-Embeddings by Autoencoding" @default.
• W2853138162 cites W1498740961 @default.
• W2853138162 cites W1576954243 @default.
• W2853138162 cites W1621714953 @default.
• W2853138162 cites W1654905138 @default.
• W2853138162 cites W1662133657 @default.
• W2853138162 cites W1959608418 @default.
• W2853138162 cites W2023736093 @default.
• W2853138162 cites W2025768430 @default.
• W2853138162 cites W2053921957 @default.
• W2853138162 cites W2080100102 @default.
• W2853138162 cites W2096873754 @default.
• W2853138162 cites W2103318667 @default.
• W2853138162 cites W2115613106 @default.
• W2853138162 cites W2117130368 @default.
• W2853138162 cites W2118090838 @default.
• W2853138162 cites W2131462252 @default.
• W2853138162 cites W2137735870 @default.
• W2853138162 cites W2145094598 @default.
• W2853138162 cites W2147152072 @default.
• W2853138162 cites W2153579005 @default.
• W2853138162 cites W2158139315 @default.
• W2853138162 cites W2158199200 @default.
• W2853138162 cites W2160660844 @default.
• W2853138162 cites W2163455955 @default.
• W2853138162 cites W2164019165 @default.
• W2853138162 cites W2202480720 @default.
• W2853138162 cites W2250189634 @default.
• W2853138162 cites W2250539671 @default.
• W2853138162 cites W2250714477 @default.
• W2853138162 cites W2251348291 @default.
• W2853138162 cites W2251939518 @default.
• W2853138162 cites W2293958442 @default.
• W2853138162 cites W2463877837 @default.
• W2853138162 cites W2510530102 @default.
• W2853138162 cites W2560366237 @default.
• W2853138162 cites W2950199579 @default.
• W2853138162 cites W2963087041 @default.
• W2853138162 cites W2963463240 @default.
• W2853138162 cites W2963659646 @default.
• W2853138162 cites W2964121744 @default.
• W2853138162 cites W2964222795 @default.
• W2853138162 cites W71795751 @default.
• W2853138162 cites W771469340 @default.
• W2853138162 hasPublicationYear "2018" @default.
• W2853138162 type Work @default.
• W2853138162 sameAs 2853138162 @default.
• W2853138162 citedByCount "32" @default.
• W2853138162 countsByYear W28531381622018 @default.
• W2853138162 countsByYear W28531381622019 @default.
• W2853138162 countsByYear W28531381622020 @default.
• W2853138162 countsByYear W28531381622021 @default.
• W2853138162 crossrefType "proceedings-article" @default.
• W2853138162 hasAuthorship W2853138162A5073503574 @default.
• W2853138162 hasAuthorship W2853138162A5076649449 @default.
• W2853138162 hasConcept C111919701 @default.
• W2853138162 hasConcept C130318100 @default.
• W2853138162 hasConcept C13280743 @default.
• W2853138162 hasConcept C143724316 @default.
• W2853138162 hasConcept C151730666 @default.
• W2853138162 hasConcept C154945302 @default.
• W2853138162 hasConcept C162324750 @default.
• W2853138162 hasConcept C184337299 @default.
• W2853138162 hasConcept C185798385 @default.
• W2853138162 hasConcept C187736073 @default.
• W2853138162 hasConcept C199360897 @default.
• W2853138162 hasConcept C204321447 @default.
• W2853138162 hasConcept C205649164 @default.
• W2853138162 hasConcept C2524010 @default.
• W2853138162 hasConcept C2777462759 @default.
• W2853138162 hasConcept C2778572836 @default.
• W2853138162 hasConcept C2778828372 @default.
• W2853138162 hasConcept C2780451532 @default.
• W2853138162 hasConcept C2781002164 @default.
• W2853138162 hasConcept C2986420190 @default.
• W2853138162 hasConcept C33923547 @default.
• W2853138162 hasConcept C41008148 @default.
• W2853138162 hasConcept C41608201 @default.
• W2853138162 hasConcept C80444323 @default.
• W2853138162 hasConcept C86803240 @default.
• W2853138162 hasConcept C90805587 @default.
• W2853138162 hasConceptScore W2853138162C111919701 @default.
• W2853138162 hasConceptScore W2853138162C130318100 @default.
• W2853138162 hasConceptScore W2853138162C13280743 @default.
• W2853138162 hasConceptScore W2853138162C143724316 @default.
• W2853138162 hasConceptScore W2853138162C151730666 @default.
• W2853138162 hasConceptScore W2853138162C154945302 @default.
• W2853138162 hasConceptScore W2853138162C162324750 @default.
• W2853138162 hasConceptScore W2853138162C184337299 @default.
• W2853138162 hasConceptScore W2853138162C185798385 @default.
• W2853138162 hasConceptScore W2853138162C187736073 @default.
• W2853138162 hasConceptScore W2853138162C199360897 @default.

• next