Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214875890> ?p ?o ?g. }
- W4214875890 endingPage "21" @default.
- W4214875890 startingPage "1" @default.
- W4214875890 abstract "Numerous attempts for hypernymy relation (e.g., dog “is-a” animal) detection have been made for resourceful languages like English, whereas efforts made for low-resource languages are scarce primarily due to lack of gold-standard datasets and suitable distributional models. Therefore, we introduce four gold-standard datasets for hypernymy detection for each of the two languages, namely, Hindi and Bengali, and two gold-standard datasets for Amharic. Another major contribution of this work is to prepare distributional thesaurus (DT) embeddings for all three languages using three different network embedding methods (DeepWalk, role2vec, and M-NMF) for the first time on these languages and to show their utility for hypernymy detection. Posing this problem as a binary classification task, we experiment with supervised classifiers like Support Vector Machine, Random Forest, and so on, and we show that these classifiers fed with DT embeddings can obtain promising results while evaluated against proposed gold-standard datasets, specifically in an experimental setup that counteracts lexical memorization. We further incorporate DT embeddings and pre-trained fastText embeddings together using two different hybrid approaches, both of which produce an excellent performance. Additionally, we validate our methodology on gold-standard English datasets as well, where we reach a comparable performance to state-of-the-art models for hypernymy detection." @default.
- W4214875890 created "2022-03-05" @default.
- W4214875890 creator A5021287757 @default.
- W4214875890 creator A5039544387 @default.
- W4214875890 creator A5043644924 @default.
- W4214875890 creator A5087412193 @default.
- W4214875890 date "2022-03-04" @default.
- W4214875890 modified "2023-09-25" @default.
- W4214875890 title "Hypernymy Detection for Low-resource Languages: A Study for Hindi, Bengali, and Amharic" @default.
- W4214875890 cites W1840435438 @default.
- W4214875890 cites W1966907789 @default.
- W4214875890 cites W2068737686 @default.
- W4214875890 cites W2131253837 @default.
- W4214875890 cites W2135891920 @default.
- W4214875890 cites W2144108169 @default.
- W4214875890 cites W2168565044 @default.
- W4214875890 cites W2250533418 @default.
- W4214875890 cites W2251331208 @default.
- W4214875890 cites W2296076036 @default.
- W4214875890 cites W2395353735 @default.
- W4214875890 cites W2493916176 @default.
- W4214875890 cites W2519468206 @default.
- W4214875890 cites W2583105957 @default.
- W4214875890 cites W2604942799 @default.
- W4214875890 cites W2734844314 @default.
- W4214875890 cites W2739709728 @default.
- W4214875890 cites W2740026090 @default.
- W4214875890 cites W2759837006 @default.
- W4214875890 cites W2760204057 @default.
- W4214875890 cites W2786152061 @default.
- W4214875890 cites W2806593956 @default.
- W4214875890 cites W2807664102 @default.
- W4214875890 cites W2882319491 @default.
- W4214875890 cites W2891375999 @default.
- W4214875890 cites W2905484073 @default.
- W4214875890 cites W2912144401 @default.
- W4214875890 cites W2952979909 @default.
- W4214875890 cites W2962700197 @default.
- W4214875890 cites W2962724755 @default.
- W4214875890 cites W2962772175 @default.
- W4214875890 cites W2962780764 @default.
- W4214875890 cites W2962814626 @default.
- W4214875890 cites W2962909572 @default.
- W4214875890 cites W2962958486 @default.
- W4214875890 cites W2962992134 @default.
- W4214875890 cites W2963173796 @default.
- W4214875890 cites W2963639153 @default.
- W4214875890 cites W2963658877 @default.
- W4214875890 cites W2963709631 @default.
- W4214875890 cites W2963846996 @default.
- W4214875890 cites W2964046079 @default.
- W4214875890 cites W2964350953 @default.
- W4214875890 cites W2987579681 @default.
- W4214875890 cites W2995133078 @default.
- W4214875890 cites W3034588514 @default.
- W4214875890 cites W3034704198 @default.
- W4214875890 cites W3104097132 @default.
- W4214875890 cites W3105971000 @default.
- W4214875890 cites W4211148418 @default.
- W4214875890 cites W2952492414 @default.
- W4214875890 doi "https://doi.org/10.1145/3490389" @default.
- W4214875890 hasPublicationYear "2022" @default.
- W4214875890 type Work @default.
- W4214875890 citedByCount "0" @default.
- W4214875890 crossrefType "journal-article" @default.
- W4214875890 hasAuthorship W4214875890A5021287757 @default.
- W4214875890 hasAuthorship W4214875890A5039544387 @default.
- W4214875890 hasAuthorship W4214875890A5043644924 @default.
- W4214875890 hasAuthorship W4214875890A5087412193 @default.
- W4214875890 hasConcept C105795698 @default.
- W4214875890 hasConcept C119857082 @default.
- W4214875890 hasConcept C12267149 @default.
- W4214875890 hasConcept C154945302 @default.
- W4214875890 hasConcept C19235068 @default.
- W4214875890 hasConcept C204321447 @default.
- W4214875890 hasConcept C2780900699 @default.
- W4214875890 hasConcept C33923547 @default.
- W4214875890 hasConcept C40993552 @default.
- W4214875890 hasConcept C41008148 @default.
- W4214875890 hasConcept C519982507 @default.
- W4214875890 hasConceptScore W4214875890C105795698 @default.
- W4214875890 hasConceptScore W4214875890C119857082 @default.
- W4214875890 hasConceptScore W4214875890C12267149 @default.
- W4214875890 hasConceptScore W4214875890C154945302 @default.
- W4214875890 hasConceptScore W4214875890C19235068 @default.
- W4214875890 hasConceptScore W4214875890C204321447 @default.
- W4214875890 hasConceptScore W4214875890C2780900699 @default.
- W4214875890 hasConceptScore W4214875890C33923547 @default.
- W4214875890 hasConceptScore W4214875890C40993552 @default.
- W4214875890 hasConceptScore W4214875890C41008148 @default.
- W4214875890 hasConceptScore W4214875890C519982507 @default.
- W4214875890 hasIssue "4" @default.
- W4214875890 hasLocation W42148758901 @default.
- W4214875890 hasOpenAccess W4214875890 @default.
- W4214875890 hasPrimaryLocation W42148758901 @default.
- W4214875890 hasRelatedWork W10843010 @default.
- W4214875890 hasRelatedWork W1593502373 @default.
- W4214875890 hasRelatedWork W1809553506 @default.