Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312546084> ?p ?o ?g. }
- W4312546084 endingPage "247" @default.
- W4312546084 startingPage "236" @default.
- W4312546084 abstract "Word embedding is a fundamental natural language processing task which can learn feature of words. However, most word embedding methods assign only one vector to a word, even if polysemous words have multi-senses. To address this limitation, we propose SememeWSD Synonym (SWSDS) model to assign a different vector to every sense of polysemous words with the help of word sense disambiguation (WSD) and synonym set in OpenHowNet. We use the SememeWSD model, an unsupervised word sense disambiguation model based on OpenHowNet, to do word sense disambiguation and annotate the polysemous word with sense id. Then, we obtain top n synonyms of the word sense from OpenHowNet and calculate the average vector of synonyms as the vector of the word sense. In experiments, We evaluate the SWSDS model on semantic similarity calculation with Gensim’s wmdistance method. It achieves improvement of accuracy. We also examine the SememeWSD model on different BERT models to find the more effective model." @default.
- W4312546084 created "2023-01-05" @default.
- W4312546084 creator A5014416571 @default.
- W4312546084 creator A5031376838 @default.
- W4312546084 creator A5040005782 @default.
- W4312546084 creator A5079322563 @default.
- W4312546084 creator A5088046237 @default.
- W4312546084 date "2022-01-01" @default.
- W4312546084 modified "2023-09-26" @default.
- W4312546084 title "Chinese Word Sense Embedding with SememeWSD and Synonym Set" @default.
- W4312546084 cites W1969096374 @default.
- W4312546084 cites W2034363849 @default.
- W4312546084 cites W2102381086 @default.
- W4312546084 cites W2118020653 @default.
- W4312546084 cites W2159719802 @default.
- W4312546084 cites W2250539671 @default.
- W4312546084 cites W2251537235 @default.
- W4312546084 cites W2401458401 @default.
- W4312546084 cites W2518202280 @default.
- W4312546084 cites W2565658037 @default.
- W4312546084 cites W2735926531 @default.
- W4312546084 cites W2740768945 @default.
- W4312546084 cites W2757205734 @default.
- W4312546084 cites W2766999827 @default.
- W4312546084 cites W2804552794 @default.
- W4312546084 cites W2909502737 @default.
- W4312546084 cites W2962739339 @default.
- W4312546084 cites W3117815199 @default.
- W4312546084 cites W3153228281 @default.
- W4312546084 cites W3187693843 @default.
- W4312546084 cites W3190490454 @default.
- W4312546084 cites W3193147816 @default.
- W4312546084 cites W3210120707 @default.
- W4312546084 cites W3213432108 @default.
- W4312546084 doi "https://doi.org/10.1007/978-3-031-20503-3_19" @default.
- W4312546084 hasPublicationYear "2022" @default.
- W4312546084 type Work @default.
- W4312546084 citedByCount "1" @default.
- W4312546084 countsByYear W43125460842023 @default.
- W4312546084 crossrefType "book-chapter" @default.
- W4312546084 hasAuthorship W4312546084A5014416571 @default.
- W4312546084 hasAuthorship W4312546084A5031376838 @default.
- W4312546084 hasAuthorship W4312546084A5040005782 @default.
- W4312546084 hasAuthorship W4312546084A5079322563 @default.
- W4312546084 hasAuthorship W4312546084A5088046237 @default.
- W4312546084 hasBestOaLocation W43125460842 @default.
- W4312546084 hasConcept C103278499 @default.
- W4312546084 hasConcept C115961682 @default.
- W4312546084 hasConcept C130318100 @default.
- W4312546084 hasConcept C138885662 @default.
- W4312546084 hasConcept C154945302 @default.
- W4312546084 hasConcept C157369684 @default.
- W4312546084 hasConcept C162324750 @default.
- W4312546084 hasConcept C173483453 @default.
- W4312546084 hasConcept C177264268 @default.
- W4312546084 hasConcept C187736073 @default.
- W4312546084 hasConcept C199360897 @default.
- W4312546084 hasConcept C204321447 @default.
- W4312546084 hasConcept C2776401178 @default.
- W4312546084 hasConcept C2777462759 @default.
- W4312546084 hasConcept C2780276568 @default.
- W4312546084 hasConcept C2780451532 @default.
- W4312546084 hasConcept C41008148 @default.
- W4312546084 hasConcept C41608201 @default.
- W4312546084 hasConcept C41895202 @default.
- W4312546084 hasConcept C44572571 @default.
- W4312546084 hasConcept C59822182 @default.
- W4312546084 hasConcept C83665646 @default.
- W4312546084 hasConcept C86803240 @default.
- W4312546084 hasConcept C90805587 @default.
- W4312546084 hasConceptScore W4312546084C103278499 @default.
- W4312546084 hasConceptScore W4312546084C115961682 @default.
- W4312546084 hasConceptScore W4312546084C130318100 @default.
- W4312546084 hasConceptScore W4312546084C138885662 @default.
- W4312546084 hasConceptScore W4312546084C154945302 @default.
- W4312546084 hasConceptScore W4312546084C157369684 @default.
- W4312546084 hasConceptScore W4312546084C162324750 @default.
- W4312546084 hasConceptScore W4312546084C173483453 @default.
- W4312546084 hasConceptScore W4312546084C177264268 @default.
- W4312546084 hasConceptScore W4312546084C187736073 @default.
- W4312546084 hasConceptScore W4312546084C199360897 @default.
- W4312546084 hasConceptScore W4312546084C204321447 @default.
- W4312546084 hasConceptScore W4312546084C2776401178 @default.
- W4312546084 hasConceptScore W4312546084C2777462759 @default.
- W4312546084 hasConceptScore W4312546084C2780276568 @default.
- W4312546084 hasConceptScore W4312546084C2780451532 @default.
- W4312546084 hasConceptScore W4312546084C41008148 @default.
- W4312546084 hasConceptScore W4312546084C41608201 @default.
- W4312546084 hasConceptScore W4312546084C41895202 @default.
- W4312546084 hasConceptScore W4312546084C44572571 @default.
- W4312546084 hasConceptScore W4312546084C59822182 @default.
- W4312546084 hasConceptScore W4312546084C83665646 @default.
- W4312546084 hasConceptScore W4312546084C86803240 @default.
- W4312546084 hasConceptScore W4312546084C90805587 @default.
- W4312546084 hasLocation W43125460841 @default.
- W4312546084 hasLocation W43125460842 @default.
- W4312546084 hasOpenAccess W4312546084 @default.
- W4312546084 hasPrimaryLocation W43125460841 @default.