Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316192634> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4316192634 abstract "While a class of data-driven approaches has been shown to be effective in embedding words of languages that are relatively simple as per inflections and compounding characteristics (e.g. English), an open area of investigation is ways of integrating language-specific characteristics within the framework of an embedding model. Standard word embedding approaches, such as word2vec, Glove etc. embed each word into a high dimensional dense vector. However, these approaches may not adequately capture the inherent linguistic phenomenon namely that of word compounding. We propose a stochastic word transformation based generalization of the skip-gram algorithm, which seeks to potentially improve the representation of the compositional compound words by leveraging information from the contexts of their constituents. Our experiments show that addressing the compounding effect of a language as a part of the word embedding objective outperforms existing methods of compounding-specific post-transformation based approaches on word semantics prediction and word polarity prediction tasks." @default.
- W4316192634 created "2023-01-15" @default.
- W4316192634 creator A5037394429 @default.
- W4316192634 creator A5082339849 @default.
- W4316192634 creator A5086918282 @default.
- W4316192634 date "2022-12-09" @default.
- W4316192634 modified "2023-09-28" @default.
- W4316192634 title "“If you can’t beat them, join them”: A Word Transformation based Generalized Skip-gram for Embedding Compound Words" @default.
- W4316192634 cites W14754660 @default.
- W4316192634 cites W1503259811 @default.
- W4316192634 cites W1531522183 @default.
- W4316192634 cites W1985514943 @default.
- W4316192634 cites W2100368767 @default.
- W4316192634 cites W2105330820 @default.
- W4316192634 cites W2134913565 @default.
- W4316192634 cites W2135413937 @default.
- W4316192634 cites W2154462503 @default.
- W4316192634 cites W2250539671 @default.
- W4316192634 cites W2493916176 @default.
- W4316192634 cites W2507731975 @default.
- W4316192634 cites W2510998959 @default.
- W4316192634 cites W2772276716 @default.
- W4316192634 cites W2797938814 @default.
- W4316192634 cites W2898914189 @default.
- W4316192634 cites W2914163459 @default.
- W4316192634 cites W2962739339 @default.
- W4316192634 cites W2963421945 @default.
- W4316192634 cites W2963477629 @default.
- W4316192634 cites W2969068412 @default.
- W4316192634 cites W2970343438 @default.
- W4316192634 cites W3007062217 @default.
- W4316192634 cites W3041864618 @default.
- W4316192634 cites W3090378332 @default.
- W4316192634 cites W3131324121 @default.
- W4316192634 cites W1999302842 @default.
- W4316192634 cites W2250612198 @default.
- W4316192634 doi "https://doi.org/10.1145/3574318.3574346" @default.
- W4316192634 hasPublicationYear "2022" @default.
- W4316192634 type Work @default.
- W4316192634 citedByCount "0" @default.
- W4316192634 crossrefType "proceedings-article" @default.
- W4316192634 hasAuthorship W4316192634A5037394429 @default.
- W4316192634 hasAuthorship W4316192634A5082339849 @default.
- W4316192634 hasAuthorship W4316192634A5086918282 @default.
- W4316192634 hasConcept C104317684 @default.
- W4316192634 hasConcept C154945302 @default.
- W4316192634 hasConcept C159110408 @default.
- W4316192634 hasConcept C184337299 @default.
- W4316192634 hasConcept C185592680 @default.
- W4316192634 hasConcept C199360897 @default.
- W4316192634 hasConcept C204241405 @default.
- W4316192634 hasConcept C204321447 @default.
- W4316192634 hasConcept C207673951 @default.
- W4316192634 hasConcept C2524010 @default.
- W4316192634 hasConcept C2776461190 @default.
- W4316192634 hasConcept C2777462759 @default.
- W4316192634 hasConcept C33923547 @default.
- W4316192634 hasConcept C41008148 @default.
- W4316192634 hasConcept C41608201 @default.
- W4316192634 hasConcept C55493867 @default.
- W4316192634 hasConcept C71924100 @default.
- W4316192634 hasConcept C90805587 @default.
- W4316192634 hasConceptScore W4316192634C104317684 @default.
- W4316192634 hasConceptScore W4316192634C154945302 @default.
- W4316192634 hasConceptScore W4316192634C159110408 @default.
- W4316192634 hasConceptScore W4316192634C184337299 @default.
- W4316192634 hasConceptScore W4316192634C185592680 @default.
- W4316192634 hasConceptScore W4316192634C199360897 @default.
- W4316192634 hasConceptScore W4316192634C204241405 @default.
- W4316192634 hasConceptScore W4316192634C204321447 @default.
- W4316192634 hasConceptScore W4316192634C207673951 @default.
- W4316192634 hasConceptScore W4316192634C2524010 @default.
- W4316192634 hasConceptScore W4316192634C2776461190 @default.
- W4316192634 hasConceptScore W4316192634C2777462759 @default.
- W4316192634 hasConceptScore W4316192634C33923547 @default.
- W4316192634 hasConceptScore W4316192634C41008148 @default.
- W4316192634 hasConceptScore W4316192634C41608201 @default.
- W4316192634 hasConceptScore W4316192634C55493867 @default.
- W4316192634 hasConceptScore W4316192634C71924100 @default.
- W4316192634 hasConceptScore W4316192634C90805587 @default.
- W4316192634 hasLocation W43161926341 @default.
- W4316192634 hasOpenAccess W4316192634 @default.
- W4316192634 hasPrimaryLocation W43161926341 @default.
- W4316192634 hasRelatedWork W2596026555 @default.
- W4316192634 hasRelatedWork W2747424680 @default.
- W4316192634 hasRelatedWork W2952874106 @default.
- W4316192634 hasRelatedWork W3036348210 @default.
- W4316192634 hasRelatedWork W3046869600 @default.
- W4316192634 hasRelatedWork W4254304201 @default.
- W4316192634 hasRelatedWork W4298857951 @default.
- W4316192634 hasRelatedWork W4313247739 @default.
- W4316192634 hasRelatedWork W4313384562 @default.
- W4316192634 hasRelatedWork W4362557444 @default.
- W4316192634 isParatext "false" @default.
- W4316192634 isRetracted "false" @default.
- W4316192634 workType "article" @default.