FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048135237> ?p ?o ?g. }

• W3048135237 endingPage "106346" @default.
• W3048135237 startingPage "106346" @default.
• W3048135237 abstract "In the last years many efforts have been spent to build word embeddings, a representational device in which word meanings are described through dense unit vectors of real numbers over a continuous, high-dimensional Euclidean space, where similarity can be interpreted as a metric. Afterwards, sense-level embeddings have been proposed to describe the meaning of senses, rather than terms. More recently, additional intermediate representations have been designed, providing a vector description for pairs 〈term,sense〉, and mapping both term and sense descriptions onto a shared semantic space. However, surprisingly enough, this wealth of approaches and resources has not been supported by a parallel refinement in the metrics used to compute semantic similarity: to date, the semantic similarity featuring two input entities is mostly computed as the maximization of some angular distance intervening between vector pairs, typically cosine similarity. In this work we introduce two novel similarity metrics to compare sense-level representations, and show that by exploiting the features of sense-embeddings it is possible to substantially improve on existing strategies, by obtaining enhanced correlation with human similarity ratings. Additionally, we argue that semantic similarity needs to be complemented by another task, involving the identification of the senses at the base of the similarity rating. We experimentally verified that the proposed metrics are beneficial when dealing with both semantic similarity task and sense identification task. The experimentation also provides a detailed how-to illustrating how six important sets of sense embeddings can be used to implement the proposed similarity metrics." @default.
• W3048135237 created "2020-08-13" @default.
• W3048135237 creator A5006446756 @default.
• W3048135237 creator A5007187027 @default.
• W3048135237 creator A5047309744 @default.
• W3048135237 date "2020-10-01" @default.
• W3048135237 modified "2023-09-27" @default.
• W3048135237 title "Novel metrics for computing semantic similarity with sense embeddings" @default.
• W3048135237 cites W1854884267 @default.
• W3048135237 cites W1965647483 @default.
• W3048135237 cites W1965923765 @default.
• W3048135237 cites W1987457675 @default.
• W3048135237 cites W1995167134 @default.
• W3048135237 cites W2014765554 @default.
• W3048135237 cites W2033200726 @default.
• W3048135237 cites W2035782089 @default.
• W3048135237 cites W2043648720 @default.
• W3048135237 cites W2059975159 @default.
• W3048135237 cites W2070150502 @default.
• W3048135237 cites W2080100102 @default.
• W3048135237 cites W2081580037 @default.
• W3048135237 cites W2087739686 @default.
• W3048135237 cites W2091785052 @default.
• W3048135237 cites W2096819730 @default.
• W3048135237 cites W2099550752 @default.
• W3048135237 cites W2112184938 @default.
• W3048135237 cites W2118452738 @default.
• W3048135237 cites W2120084270 @default.
• W3048135237 cites W2124439780 @default.
• W3048135237 cites W2127289991 @default.
• W3048135237 cites W2136930489 @default.
• W3048135237 cites W2141528665 @default.
• W3048135237 cites W2158997610 @default.
• W3048135237 cites W2192710297 @default.
• W3048135237 cites W2250539671 @default.
• W3048135237 cites W2436001372 @default.
• W3048135237 cites W2439017901 @default.
• W3048135237 cites W2473542931 @default.
• W3048135237 cites W2490986620 @default.
• W3048135237 cites W2517456239 @default.
• W3048135237 cites W2567035470 @default.
• W3048135237 cites W2573280870 @default.
• W3048135237 cites W2753628379 @default.
• W3048135237 cites W2791766977 @default.
• W3048135237 cites W2809683153 @default.
• W3048135237 cites W2882319491 @default.
• W3048135237 cites W2951457034 @default.
• W3048135237 cites W2962739339 @default.
• W3048135237 cites W2963123788 @default.
• W3048135237 cites W2963832429 @default.
• W3048135237 cites W2963850840 @default.
• W3048135237 cites W2963947304 @default.
• W3048135237 cites W2964109882 @default.
• W3048135237 cites W3013895536 @default.
• W3048135237 cites W3083588163 @default.
• W3048135237 cites W4254579240 @default.
• W3048135237 cites W4292157289 @default.
• W3048135237 doi "https://doi.org/10.1016/j.knosys.2020.106346" @default.
• W3048135237 hasPublicationYear "2020" @default.
• W3048135237 type Work @default.
• W3048135237 sameAs 3048135237 @default.
• W3048135237 citedByCount "6" @default.
• W3048135237 countsByYear W30481352372021 @default.
• W3048135237 countsByYear W30481352372022 @default.
• W3048135237 crossrefType "journal-article" @default.
• W3048135237 hasAuthorship W3048135237A5006446756 @default.
• W3048135237 hasAuthorship W3048135237A5007187027 @default.
• W3048135237 hasAuthorship W3048135237A5047309744 @default.
• W3048135237 hasConcept C103278499 @default.
• W3048135237 hasConcept C115961682 @default.
• W3048135237 hasConcept C116834253 @default.
• W3048135237 hasConcept C120174047 @default.
• W3048135237 hasConcept C121332964 @default.
• W3048135237 hasConcept C130318100 @default.
• W3048135237 hasConcept C153180895 @default.
• W3048135237 hasConcept C154945302 @default.
• W3048135237 hasConcept C162324750 @default.
• W3048135237 hasConcept C176217482 @default.
• W3048135237 hasConcept C187736073 @default.
• W3048135237 hasConcept C204321447 @default.
• W3048135237 hasConcept C21547014 @default.
• W3048135237 hasConcept C23123220 @default.
• W3048135237 hasConcept C2524010 @default.
• W3048135237 hasConcept C2780451532 @default.
• W3048135237 hasConcept C2780762811 @default.
• W3048135237 hasConcept C33923547 @default.
• W3048135237 hasConcept C41008148 @default.
• W3048135237 hasConcept C59822182 @default.
• W3048135237 hasConcept C61797465 @default.
• W3048135237 hasConcept C62520636 @default.
• W3048135237 hasConcept C80444323 @default.
• W3048135237 hasConcept C86803240 @default.
• W3048135237 hasConcept C90805587 @default.
• W3048135237 hasConceptScore W3048135237C103278499 @default.
• W3048135237 hasConceptScore W3048135237C115961682 @default.
• W3048135237 hasConceptScore W3048135237C116834253 @default.
• W3048135237 hasConceptScore W3048135237C120174047 @default.
• W3048135237 hasConceptScore W3048135237C121332964 @default.

• next