FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3146034405> ?p ?o ?g. }

• W3146034405 abstract "We tackle the problem of identifying metaphors in text, treated as a sequence tagging task. The pre-trained word embeddings GloVe, ELMo and BERT have individually shown good performance on sequential metaphor identification. These embeddings are generated by different models, training targets and corpora, thus encoding different semantic and syntactic information. We show that leveraging GloVe, ELMo and feature-based BERT based on a multi-channel CNN and a Bidirectional LSTM model can significantly outperform any single word embedding method and the combination of the two embeddings. Incorporating linguistic features into our model can further improve model performance, yielding state-of-the-art performance on three public metaphor datasets. We also provide in-depth analysis on the effectiveness of leveraging multiple word embeddings, including analysing the spatial distribution of different embedding methods for metaphors and literals, and showing how well the embeddings complement each other in different genres and parts of speech." @default.
• W3146034405 created "2021-04-13" @default.
• W3146034405 creator A5024599321 @default.
• W3146034405 creator A5062187850 @default.
• W3146034405 creator A5090217029 @default.
• W3146034405 date "2021-04-07" @default.
• W3146034405 modified "2023-09-27" @default.
• W3146034405 title "Combining Pre-trained Word Embeddings and Linguistic Features for Sequential Metaphor Identification" @default.
• W3146034405 cites W1561412240 @default.
• W3146034405 cites W1832693441 @default.
• W3146034405 cites W2011019567 @default.
• W3146034405 cites W2024754409 @default.
• W3146034405 cites W2038721957 @default.
• W3146034405 cites W2101217916 @default.
• W3146034405 cites W2109057934 @default.
• W3146034405 cites W2115340919 @default.
• W3146034405 cites W2126530744 @default.
• W3146034405 cites W2153579005 @default.
• W3146034405 cites W2165131017 @default.
• W3146034405 cites W2250539671 @default.
• W3146034405 cites W2252218513 @default.
• W3146034405 cites W2294774419 @default.
• W3146034405 cites W2427312199 @default.
• W3146034405 cites W2470413457 @default.
• W3146034405 cites W2515860461 @default.
• W3146034405 cites W2560778841 @default.
• W3146034405 cites W2742947407 @default.
• W3146034405 cites W2762484717 @default.
• W3146034405 cites W2798651446 @default.
• W3146034405 cites W2806273110 @default.
• W3146034405 cites W2806592685 @default.
• W3146034405 cites W2890236535 @default.
• W3146034405 cites W2915128308 @default.
• W3146034405 cites W2949433733 @default.
• W3146034405 cites W2949442961 @default.
• W3146034405 cites W2962739339 @default.
• W3146034405 cites W2962741379 @default.
• W3146034405 cites W2962748048 @default.
• W3146034405 cites W2962814195 @default.
• W3146034405 cites W2963272610 @default.
• W3146034405 cites W2963341956 @default.
• W3146034405 cites W2963403868 @default.
• W3146034405 cites W2964303116 @default.
• W3146034405 cites W2970727289 @default.
• W3146034405 cites W3023058184 @default.
• W3146034405 doi "https://doi.org/10.48550/arxiv.2104.03285" @default.
• W3146034405 hasPublicationYear "2021" @default.
• W3146034405 type Work @default.
• W3146034405 sameAs 3146034405 @default.
• W3146034405 citedByCount "0" @default.
• W3146034405 crossrefType "posted-content" @default.
• W3146034405 hasAuthorship W3146034405A5024599321 @default.
• W3146034405 hasAuthorship W3146034405A5062187850 @default.
• W3146034405 hasAuthorship W3146034405A5090217029 @default.
• W3146034405 hasBestOaLocation W31460344051 @default.
• W3146034405 hasConcept C104317684 @default.
• W3146034405 hasConcept C112313634 @default.
• W3146034405 hasConcept C116834253 @default.
• W3146034405 hasConcept C125411270 @default.
• W3146034405 hasConcept C127716648 @default.
• W3146034405 hasConcept C138885662 @default.
• W3146034405 hasConcept C154945302 @default.
• W3146034405 hasConcept C162324750 @default.
• W3146034405 hasConcept C185592680 @default.
• W3146034405 hasConcept C187736073 @default.
• W3146034405 hasConcept C188082640 @default.
• W3146034405 hasConcept C204321447 @default.
• W3146034405 hasConcept C2776401178 @default.
• W3146034405 hasConcept C2777462759 @default.
• W3146034405 hasConcept C2778311575 @default.
• W3146034405 hasConcept C2780451532 @default.
• W3146034405 hasConcept C28490314 @default.
• W3146034405 hasConcept C35639132 @default.
• W3146034405 hasConcept C41008148 @default.
• W3146034405 hasConcept C41608201 @default.
• W3146034405 hasConcept C41895202 @default.
• W3146034405 hasConcept C55493867 @default.
• W3146034405 hasConcept C59822182 @default.
• W3146034405 hasConcept C86803240 @default.
• W3146034405 hasConcept C90805587 @default.
• W3146034405 hasConceptScore W3146034405C104317684 @default.
• W3146034405 hasConceptScore W3146034405C112313634 @default.
• W3146034405 hasConceptScore W3146034405C116834253 @default.
• W3146034405 hasConceptScore W3146034405C125411270 @default.
• W3146034405 hasConceptScore W3146034405C127716648 @default.
• W3146034405 hasConceptScore W3146034405C138885662 @default.
• W3146034405 hasConceptScore W3146034405C154945302 @default.
• W3146034405 hasConceptScore W3146034405C162324750 @default.
• W3146034405 hasConceptScore W3146034405C185592680 @default.
• W3146034405 hasConceptScore W3146034405C187736073 @default.
• W3146034405 hasConceptScore W3146034405C188082640 @default.
• W3146034405 hasConceptScore W3146034405C204321447 @default.
• W3146034405 hasConceptScore W3146034405C2776401178 @default.
• W3146034405 hasConceptScore W3146034405C2777462759 @default.
• W3146034405 hasConceptScore W3146034405C2778311575 @default.
• W3146034405 hasConceptScore W3146034405C2780451532 @default.
• W3146034405 hasConceptScore W3146034405C28490314 @default.
• W3146034405 hasConceptScore W3146034405C35639132 @default.
• W3146034405 hasConceptScore W3146034405C41008148 @default.
• W3146034405 hasConceptScore W3146034405C41608201 @default.

• next