Matches in SemOpenAlex for { <https://semopenalex.org/work/W2968795812> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2968795812 abstract "State of the art works for Point-Of-Interest (POI) classification use either traditional feature extraction methods, or, more recently, deep learning (DL) methods, in order to train classification models on historical data, i.e. POIs already annotated with categories, and then deploy these models to classify new, unannotated POIs. These methods are either inherently limited to learning simple, rather than complex, relationships, or learn embeddings trivially and without taking into account domain knowledge or semantic information, thus yielding disappointing classification results. In this vision paper, we discuss the problem of POI classification, identify limitations in the state of the art and propose novel research directions. We propose a framework for learning meaningful context embeddings for POIs, that incorporate domain knowledge and semantic information extracted from external data sources, and we discuss how the proposed approach can overcome inherent limitations of the state of the art. Specifically, we prescribe the construction of fine-grained embeddings, by refining the consideration of spatial neighborhoods of POIs, assessing and selecting the proper attributes to be used as context and target information in the embedding learning process, as well as by properly enriching these embeddings with external, semantic knowledge. Additionally, we advocate the joint utilization of traditional training features and embedding-derived features for POI classification, and argue towards the usefulness of the proposed approach." @default.
- W2968795812 created "2019-08-22" @default.
- W2968795812 creator A5037415488 @default.
- W2968795812 creator A5083625529 @default.
- W2968795812 date "2019-08-19" @default.
- W2968795812 modified "2023-09-25" @default.
- W2968795812 title "Learning Domain Driven and Semantically Enriched Embeddings for POI Classification" @default.
- W2968795812 cites W2026959997 @default.
- W2968795812 cites W2057143829 @default.
- W2968795812 cites W2074304123 @default.
- W2968795812 cites W2462720196 @default.
- W2968795812 cites W2523679382 @default.
- W2968795812 cites W2740143455 @default.
- W2968795812 cites W2743187225 @default.
- W2968795812 cites W2763768291 @default.
- W2968795812 cites W2767597557 @default.
- W2968795812 cites W2776890924 @default.
- W2968795812 cites W2788167626 @default.
- W2968795812 cites W2964057288 @default.
- W2968795812 doi "https://doi.org/10.1145/3340964.3340992" @default.
- W2968795812 hasPublicationYear "2019" @default.
- W2968795812 type Work @default.
- W2968795812 sameAs 2968795812 @default.
- W2968795812 citedByCount "2" @default.
- W2968795812 countsByYear W29687958122020 @default.
- W2968795812 countsByYear W29687958122023 @default.
- W2968795812 crossrefType "proceedings-article" @default.
- W2968795812 hasAuthorship W2968795812A5037415488 @default.
- W2968795812 hasAuthorship W2968795812A5083625529 @default.
- W2968795812 hasConcept C111919701 @default.
- W2968795812 hasConcept C119857082 @default.
- W2968795812 hasConcept C134306372 @default.
- W2968795812 hasConcept C138885662 @default.
- W2968795812 hasConcept C150140777 @default.
- W2968795812 hasConcept C151730666 @default.
- W2968795812 hasConcept C154945302 @default.
- W2968795812 hasConcept C23123220 @default.
- W2968795812 hasConcept C2776401178 @default.
- W2968795812 hasConcept C2779343474 @default.
- W2968795812 hasConcept C33923547 @default.
- W2968795812 hasConcept C36503486 @default.
- W2968795812 hasConcept C41008148 @default.
- W2968795812 hasConcept C41608201 @default.
- W2968795812 hasConcept C41895202 @default.
- W2968795812 hasConcept C86803240 @default.
- W2968795812 hasConcept C98045186 @default.
- W2968795812 hasConceptScore W2968795812C111919701 @default.
- W2968795812 hasConceptScore W2968795812C119857082 @default.
- W2968795812 hasConceptScore W2968795812C134306372 @default.
- W2968795812 hasConceptScore W2968795812C138885662 @default.
- W2968795812 hasConceptScore W2968795812C150140777 @default.
- W2968795812 hasConceptScore W2968795812C151730666 @default.
- W2968795812 hasConceptScore W2968795812C154945302 @default.
- W2968795812 hasConceptScore W2968795812C23123220 @default.
- W2968795812 hasConceptScore W2968795812C2776401178 @default.
- W2968795812 hasConceptScore W2968795812C2779343474 @default.
- W2968795812 hasConceptScore W2968795812C33923547 @default.
- W2968795812 hasConceptScore W2968795812C36503486 @default.
- W2968795812 hasConceptScore W2968795812C41008148 @default.
- W2968795812 hasConceptScore W2968795812C41608201 @default.
- W2968795812 hasConceptScore W2968795812C41895202 @default.
- W2968795812 hasConceptScore W2968795812C86803240 @default.
- W2968795812 hasConceptScore W2968795812C98045186 @default.
- W2968795812 hasLocation W29687958121 @default.
- W2968795812 hasOpenAccess W2968795812 @default.
- W2968795812 hasPrimaryLocation W29687958121 @default.
- W2968795812 hasRelatedWork W1609649892 @default.
- W2968795812 hasRelatedWork W2357241418 @default.
- W2968795812 hasRelatedWork W2366644548 @default.
- W2968795812 hasRelatedWork W2376314740 @default.
- W2968795812 hasRelatedWork W2384888906 @default.
- W2968795812 hasRelatedWork W2961085424 @default.
- W2968795812 hasRelatedWork W3043346077 @default.
- W2968795812 hasRelatedWork W4286629047 @default.
- W2968795812 hasRelatedWork W4306674287 @default.
- W2968795812 hasRelatedWork W4224009465 @default.
- W2968795812 isParatext "false" @default.
- W2968795812 isRetracted "false" @default.
- W2968795812 magId "2968795812" @default.
- W2968795812 workType "article" @default.