FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3104336196> ?p ?o ?g. }

• W3104336196 abstract "Mainstream computational lexical semantics embraces the assumption that word senses can be represented as discrete items of a predefined inventory. In this paper we show this needs not be the case, and propose a unified model that is able to produce contextually appropriate definitions. In our model, Generationary, we employ a novel span-based encoding scheme which we use to fine-tune an English pre-trained Encoder-Decoder system to generate glosses. We show that, even though we drop the need of choosing from a predefined sense inventory, our model can be employed effectively: not only does Generationary outperform previous approaches in the generative task of Definition Modeling in many settings, but it also matches or surpasses the state of the art in discriminative tasks such as Word Sense Disambiguation and Word-in-Context. Finally, we show that Generationary benefits from training on data from multiple inventories, with strong gains on various zero-shot benchmarks, including a novel dataset of definitions for free adjective-noun phrases. The software and reproduction materials are available at http://generationary.org." @default.
• W3104336196 created "2020-11-23" @default.
• W3104336196 creator A5026648049 @default.
• W3104336196 creator A5076412131 @default.
• W3104336196 creator A5079283776 @default.
• W3104336196 date "2020-01-01" @default.
• W3104336196 modified "2023-09-27" @default.
• W3104336196 title "Generationary or “How We Went beyond Word Sense Inventories and Learned to Gloss”" @default.
• W3104336196 cites W135437175 @default.
• W3104336196 cites W1509525679 @default.
• W3104336196 cites W1572948005 @default.
• W3104336196 cites W1731542712 @default.
• W3104336196 cites W2000255081 @default.
• W3104336196 cites W2026261675 @default.
• W3104336196 cites W2031026221 @default.
• W3104336196 cites W2038721957 @default.
• W3104336196 cites W2041219519 @default.
• W3104336196 cites W2065157922 @default.
• W3104336196 cites W2095980407 @default.
• W3104336196 cites W2123301721 @default.
• W3104336196 cites W2131540451 @default.
• W3104336196 cites W2136657878 @default.
• W3104336196 cites W2143017621 @default.
• W3104336196 cites W2154652894 @default.
• W3104336196 cites W2251529656 @default.
• W3104336196 cites W2436001372 @default.
• W3104336196 cites W2599992093 @default.
• W3104336196 cites W2604799547 @default.
• W3104336196 cites W2740782137 @default.
• W3104336196 cites W2798287132 @default.
• W3104336196 cites W2836780890 @default.
• W3104336196 cites W2889801236 @default.
• W3104336196 cites W2896062597 @default.
• W3104336196 cites W2946748737 @default.
• W3104336196 cites W2950502294 @default.
• W3104336196 cites W2951539960 @default.
• W3104336196 cites W2956105246 @default.
• W3104336196 cites W2962987965 @default.
• W3104336196 cites W2963532001 @default.
• W3104336196 cites W2964303159 @default.
• W3104336196 cites W2970662235 @default.
• W3104336196 cites W2970667782 @default.
• W3104336196 cites W2970773744 @default.
• W3104336196 cites W2974300509 @default.
• W3104336196 cites W2996403597 @default.
• W3104336196 cites W2997292130 @default.
• W3104336196 cites W3011373955 @default.
• W3104336196 cites W3017887871 @default.
• W3104336196 cites W3034782826 @default.
• W3104336196 cites W3035507081 @default.
• W3104336196 cites W3035753217 @default.
• W3104336196 cites W3038047120 @default.
• W3104336196 cites W3041518139 @default.
• W3104336196 cites W3101094968 @default.
• W3104336196 doi "https://doi.org/10.18653/v1/2020.emnlp-main.585" @default.
• W3104336196 hasPublicationYear "2020" @default.
• W3104336196 type Work @default.
• W3104336196 sameAs 3104336196 @default.
• W3104336196 citedByCount "13" @default.
• W3104336196 countsByYear W31043361962020 @default.
• W3104336196 countsByYear W31043361962021 @default.
• W3104336196 countsByYear W31043361962022 @default.
• W3104336196 countsByYear W31043361962023 @default.
• W3104336196 crossrefType "proceedings-article" @default.
• W3104336196 hasAuthorship W3104336196A5026648049 @default.
• W3104336196 hasAuthorship W3104336196A5076412131 @default.
• W3104336196 hasAuthorship W3104336196A5079283776 @default.
• W3104336196 hasBestOaLocation W31043361961 @default.
• W3104336196 hasConcept C111919701 @default.
• W3104336196 hasConcept C118505674 @default.
• W3104336196 hasConcept C121934690 @default.
• W3104336196 hasConcept C138885662 @default.
• W3104336196 hasConcept C154945302 @default.
• W3104336196 hasConcept C204321447 @default.
• W3104336196 hasConcept C2777683214 @default.
• W3104336196 hasConcept C39890363 @default.
• W3104336196 hasConcept C41008148 @default.
• W3104336196 hasConcept C41895202 @default.
• W3104336196 hasConcept C90805587 @default.
• W3104336196 hasConcept C97931131 @default.
• W3104336196 hasConceptScore W3104336196C111919701 @default.
• W3104336196 hasConceptScore W3104336196C118505674 @default.
• W3104336196 hasConceptScore W3104336196C121934690 @default.
• W3104336196 hasConceptScore W3104336196C138885662 @default.
• W3104336196 hasConceptScore W3104336196C154945302 @default.
• W3104336196 hasConceptScore W3104336196C204321447 @default.
• W3104336196 hasConceptScore W3104336196C2777683214 @default.
• W3104336196 hasConceptScore W3104336196C39890363 @default.
• W3104336196 hasConceptScore W3104336196C41008148 @default.
• W3104336196 hasConceptScore W3104336196C41895202 @default.
• W3104336196 hasConceptScore W3104336196C90805587 @default.
• W3104336196 hasConceptScore W3104336196C97931131 @default.
• W3104336196 hasLocation W31043361961 @default.
• W3104336196 hasLocation W31043361962 @default.
• W3104336196 hasOpenAccess W3104336196 @default.
• W3104336196 hasPrimaryLocation W31043361961 @default.
• W3104336196 hasRelatedWork W1491200339 @default.
• W3104336196 hasRelatedWork W1975923800 @default.
• W3104336196 hasRelatedWork W1995736631 @default.
• W3104336196 hasRelatedWork W2067929605 @default.

• next