FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205374543> ?p ?o ?g. }

• W3205374543 abstract "We present a word-sense induction method based on pre-trained masked language models (MLMs), which can cheaply scale to large vocabularies and large corpora. The result is a corpus which is sense-tagged according to a corpus-derived sense inventory and where each sense is associated with indicative words. Evaluation on English Wikipedia that was sense-tagged using our method shows that both the induced senses, and the per-instance sense assignment, are of high quality even compared to WSD methods, such as Babelfy. Furthermore, by training a static word embeddings algorithm on the sense-tagged corpus, we obtain high-quality static senseful embeddings. These outperform existing senseful embeddings methods on the WiC dataset and on a new outlier detection dataset we developed. The data driven nature of the algorithm allows to induce corpora-specific senses, which may not appear in standard sense inventories, as we demonstrate using a case study on the scientific domain." @default.
• W3205374543 created "2021-10-25" @default.
• W3205374543 creator A5028476919 @default.
• W3205374543 creator A5033657404 @default.
• W3205374543 creator A5035283714 @default.
• W3205374543 creator A5046322107 @default.
• W3205374543 date "2022-01-01" @default.
• W3205374543 modified "2023-10-14" @default.
• W3205374543 title "Large Scale Substitution-based Word Sense Induction" @default.
• W3205374543 cites W1513911358 @default.
• W3205374543 cites W168564468 @default.
• W3205374543 cites W2045208889 @default.
• W3205374543 cites W2101293500 @default.
• W3205374543 cites W2102153514 @default.
• W3205374543 cites W2117805747 @default.
• W3205374543 cites W2121678312 @default.
• W3205374543 cites W2127289991 @default.
• W3205374543 cites W2131681506 @default.
• W3205374543 cites W2153579005 @default.
• W3205374543 cites W2161669948 @default.
• W3205374543 cites W2164019165 @default.
• W3205374543 cites W2164973920 @default.
• W3205374543 cites W2185315851 @default.
• W3205374543 cites W2189518090 @default.
• W3205374543 cites W2250418535 @default.
• W3205374543 cites W2250539671 @default.
• W3205374543 cites W2250962194 @default.
• W3205374543 cites W2251537235 @default.
• W3205374543 cites W2497040301 @default.
• W3205374543 cites W2507974895 @default.
• W3205374543 cites W2518587255 @default.
• W3205374543 cites W2522668296 @default.
• W3205374543 cites W2550186622 @default.
• W3205374543 cites W2574767818 @default.
• W3205374543 cites W2888282873 @default.
• W3205374543 cites W2947915358 @default.
• W3205374543 cites W2949254265 @default.
• W3205374543 cites W2956105246 @default.
• W3205374543 cites W2963341956 @default.
• W3205374543 cites W2963606136 @default.
• W3205374543 cites W2963706278 @default.
• W3205374543 cites W2963850840 @default.
• W3205374543 cites W2965105341 @default.
• W3205374543 cites W2970771982 @default.
• W3205374543 cites W3013895536 @default.
• W3205374543 cites W3037363161 @default.
• W3205374543 cites W3146681443 @default.
• W3205374543 cites W3155248473 @default.
• W3205374543 cites W64820227 @default.
• W3205374543 cites W70010159 @default.
• W3205374543 doi "https://doi.org/10.18653/v1/2022.acl-long.325" @default.
• W3205374543 hasPublicationYear "2022" @default.
• W3205374543 type Work @default.
• W3205374543 sameAs 3205374543 @default.
• W3205374543 citedByCount "1" @default.
• W3205374543 countsByYear W32053745432023 @default.
• W3205374543 crossrefType "proceedings-article" @default.
• W3205374543 hasAuthorship W3205374543A5028476919 @default.
• W3205374543 hasAuthorship W3205374543A5033657404 @default.
• W3205374543 hasAuthorship W3205374543A5035283714 @default.
• W3205374543 hasAuthorship W3205374543A5046322107 @default.
• W3205374543 hasBestOaLocation W32053745431 @default.
• W3205374543 hasConcept C111472728 @default.
• W3205374543 hasConcept C119599485 @default.
• W3205374543 hasConcept C121332964 @default.
• W3205374543 hasConcept C127413603 @default.
• W3205374543 hasConcept C134306372 @default.
• W3205374543 hasConcept C138885662 @default.
• W3205374543 hasConcept C143141573 @default.
• W3205374543 hasConcept C154945302 @default.
• W3205374543 hasConcept C15744967 @default.
• W3205374543 hasConcept C157659113 @default.
• W3205374543 hasConcept C199360897 @default.
• W3205374543 hasConcept C204321447 @default.
• W3205374543 hasConcept C2778220771 @default.
• W3205374543 hasConcept C2778755073 @default.
• W3205374543 hasConcept C2779530757 @default.
• W3205374543 hasConcept C2994427434 @default.
• W3205374543 hasConcept C33923547 @default.
• W3205374543 hasConcept C36503486 @default.
• W3205374543 hasConcept C41008148 @default.
• W3205374543 hasConcept C41895202 @default.
• W3205374543 hasConcept C51646954 @default.
• W3205374543 hasConcept C62520636 @default.
• W3205374543 hasConcept C77805123 @default.
• W3205374543 hasConcept C79337645 @default.
• W3205374543 hasConcept C90805587 @default.
• W3205374543 hasConceptScore W3205374543C111472728 @default.
• W3205374543 hasConceptScore W3205374543C119599485 @default.
• W3205374543 hasConceptScore W3205374543C121332964 @default.
• W3205374543 hasConceptScore W3205374543C127413603 @default.
• W3205374543 hasConceptScore W3205374543C134306372 @default.
• W3205374543 hasConceptScore W3205374543C138885662 @default.
• W3205374543 hasConceptScore W3205374543C143141573 @default.
• W3205374543 hasConceptScore W3205374543C154945302 @default.
• W3205374543 hasConceptScore W3205374543C15744967 @default.
• W3205374543 hasConceptScore W3205374543C157659113 @default.
• W3205374543 hasConceptScore W3205374543C199360897 @default.
• W3205374543 hasConceptScore W3205374543C204321447 @default.
• W3205374543 hasConceptScore W3205374543C2778220771 @default.

• next