Matches in SemOpenAlex for { <https://semopenalex.org/work/W3045737996> ?p ?o ?g. }
- W3045737996 abstract "Presence of near identical, but distinct, entities called entity variations makes the task of data integration challenging. For example, in the domain of grocery products, variations share the same value for attributes such as brand, manufacturer and product line, but differ in other attributes, called variational attributes, such as package size and color. Identifying variations across data sources is an important task in itself and is crucial for identifying duplicates. However, this task is challenging as the variational attributes are often present as a part of unstructured text and are domain dependent. In this work, we propose our approach, Contrastive entity linkage, to identify both entity pairs that are the same and pairs that are variations of each other. We propose a novel unsupervised approach, VarSpot, to mine domain-dependent variational attributes present in unstructured text. The proposed approach reasons about both similarities and differences between entities and can easily scale to large sources containing millions of entities. We show the generality of our approach by performing experimental evaluation on three different domains. Our approach significantly outperforms state-of-the-art learning-based and rule-based entity linkage systems by up to 4% F1 score when identifying duplicates, and up to 41% when identifying entity variations." @default.
- W3045737996 created "2020-08-03" @default.
- W3045737996 creator A5013916504 @default.
- W3045737996 creator A5024143433 @default.
- W3045737996 creator A5035605036 @default.
- W3045737996 creator A5036511132 @default.
- W3045737996 creator A5086169451 @default.
- W3045737996 creator A5088720980 @default.
- W3045737996 date "2020-06-22" @default.
- W3045737996 modified "2023-09-23" @default.
- W3045737996 title "Contrastive Entity Linkage: Mining Variational Attributes From Large Catalogs for Entity Linkage" @default.
- W3045737996 hasPublicationYear "2020" @default.
- W3045737996 type Work @default.
- W3045737996 sameAs 3045737996 @default.
- W3045737996 citedByCount "1" @default.
- W3045737996 countsByYear W30457379962021 @default.
- W3045737996 crossrefType "proceedings-article" @default.
- W3045737996 hasAuthorship W3045737996A5013916504 @default.
- W3045737996 hasAuthorship W3045737996A5024143433 @default.
- W3045737996 hasAuthorship W3045737996A5035605036 @default.
- W3045737996 hasAuthorship W3045737996A5036511132 @default.
- W3045737996 hasAuthorship W3045737996A5086169451 @default.
- W3045737996 hasAuthorship W3045737996A5088720980 @default.
- W3045737996 hasConcept C104317684 @default.
- W3045737996 hasConcept C119857082 @default.
- W3045737996 hasConcept C121332964 @default.
- W3045737996 hasConcept C124101348 @default.
- W3045737996 hasConcept C134306372 @default.
- W3045737996 hasConcept C154945302 @default.
- W3045737996 hasConcept C15744967 @default.
- W3045737996 hasConcept C162324750 @default.
- W3045737996 hasConcept C185592680 @default.
- W3045737996 hasConcept C187736073 @default.
- W3045737996 hasConcept C204321447 @default.
- W3045737996 hasConcept C23123220 @default.
- W3045737996 hasConcept C2524010 @default.
- W3045737996 hasConcept C2778334786 @default.
- W3045737996 hasConcept C2780451532 @default.
- W3045737996 hasConcept C2780767217 @default.
- W3045737996 hasConcept C31266012 @default.
- W3045737996 hasConcept C33923547 @default.
- W3045737996 hasConcept C36503486 @default.
- W3045737996 hasConcept C41008148 @default.
- W3045737996 hasConcept C44870925 @default.
- W3045737996 hasConcept C4554734 @default.
- W3045737996 hasConcept C542102704 @default.
- W3045737996 hasConcept C55493867 @default.
- W3045737996 hasConcept C90673727 @default.
- W3045737996 hasConcept C96711827 @default.
- W3045737996 hasConceptScore W3045737996C104317684 @default.
- W3045737996 hasConceptScore W3045737996C119857082 @default.
- W3045737996 hasConceptScore W3045737996C121332964 @default.
- W3045737996 hasConceptScore W3045737996C124101348 @default.
- W3045737996 hasConceptScore W3045737996C134306372 @default.
- W3045737996 hasConceptScore W3045737996C154945302 @default.
- W3045737996 hasConceptScore W3045737996C15744967 @default.
- W3045737996 hasConceptScore W3045737996C162324750 @default.
- W3045737996 hasConceptScore W3045737996C185592680 @default.
- W3045737996 hasConceptScore W3045737996C187736073 @default.
- W3045737996 hasConceptScore W3045737996C204321447 @default.
- W3045737996 hasConceptScore W3045737996C23123220 @default.
- W3045737996 hasConceptScore W3045737996C2524010 @default.
- W3045737996 hasConceptScore W3045737996C2778334786 @default.
- W3045737996 hasConceptScore W3045737996C2780451532 @default.
- W3045737996 hasConceptScore W3045737996C2780767217 @default.
- W3045737996 hasConceptScore W3045737996C31266012 @default.
- W3045737996 hasConceptScore W3045737996C33923547 @default.
- W3045737996 hasConceptScore W3045737996C36503486 @default.
- W3045737996 hasConceptScore W3045737996C41008148 @default.
- W3045737996 hasConceptScore W3045737996C44870925 @default.
- W3045737996 hasConceptScore W3045737996C4554734 @default.
- W3045737996 hasConceptScore W3045737996C542102704 @default.
- W3045737996 hasConceptScore W3045737996C55493867 @default.
- W3045737996 hasConceptScore W3045737996C90673727 @default.
- W3045737996 hasConceptScore W3045737996C96711827 @default.
- W3045737996 hasLocation W30457379961 @default.
- W3045737996 hasOpenAccess W3045737996 @default.
- W3045737996 hasPrimaryLocation W30457379961 @default.
- W3045737996 hasRelatedWork W2357360952 @default.
- W3045737996 hasRelatedWork W2473455520 @default.
- W3045737996 hasRelatedWork W2493882013 @default.
- W3045737996 hasRelatedWork W254752962 @default.
- W3045737996 hasRelatedWork W2754293325 @default.
- W3045737996 hasRelatedWork W2806845383 @default.
- W3045737996 hasRelatedWork W2885324703 @default.
- W3045737996 hasRelatedWork W2903963001 @default.
- W3045737996 hasRelatedWork W2940997877 @default.
- W3045737996 hasRelatedWork W2948644107 @default.
- W3045737996 hasRelatedWork W2969324147 @default.
- W3045737996 hasRelatedWork W2971019153 @default.
- W3045737996 hasRelatedWork W2983024903 @default.
- W3045737996 hasRelatedWork W2985009327 @default.
- W3045737996 hasRelatedWork W3006766812 @default.
- W3045737996 hasRelatedWork W3140409011 @default.
- W3045737996 hasRelatedWork W3156617631 @default.
- W3045737996 hasRelatedWork W3173197807 @default.
- W3045737996 hasRelatedWork W3182864067 @default.
- W3045737996 hasRelatedWork W4657079 @default.
- W3045737996 isParatext "false" @default.
- W3045737996 isRetracted "false" @default.