Matches in SemOpenAlex for { <https://semopenalex.org/work/W2808250782> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2808250782 abstract "Different well-established NLP tasks contribute to elicit the semantics of entities mentioned in natural language text, such as Named Entity Recognition and Classification (NERC) and Entity Linking (EL). However, combining the outcomes of these tasks may result in NLP annotations --- such as a NERC organization linked by EL to a person --- that are unlikely or contradictory when interpreted in the light of common world knowledge about the entities these annotations refer to. We thus propose a general probabilistic model that explicitly captures the relations between multiple NLP annotations for an entity mention, the ontological entity classes implied by those annotations, and the background ontological knowledge those classes may be consistent with. We use the model to estimate the posterior probability of NLP annotations given their confidences (prior probabilities) and the ontological knowledge, and consequently revise the best annotation choice performed by the NLP tools. In a concrete scenario with two state-of-the-art tools for NERC and EL, we experimentally show on three reference datasets that for these tasks, the joint annotation revision performed by the model consistently improves on the original results of the tools." @default.
- W2808250782 created "2018-06-21" @default.
- W2808250782 creator A5043305308 @default.
- W2808250782 creator A5046660236 @default.
- W2808250782 date "2018-07-01" @default.
- W2808250782 modified "2023-10-14" @default.
- W2808250782 title "Joint Posterior Revision of NLP Annotations via Ontological Knowledge" @default.
- W2808250782 cites W11298561 @default.
- W2808250782 cites W1851477384 @default.
- W2808250782 cites W2016225813 @default.
- W2808250782 cites W2016753842 @default.
- W2808250782 cites W2026810221 @default.
- W2808250782 cites W2053299703 @default.
- W2808250782 cites W2096765155 @default.
- W2808250782 cites W2122865749 @default.
- W2808250782 cites W2138204945 @default.
- W2808250782 cites W2167571757 @default.
- W2808250782 cites W2181629536 @default.
- W2808250782 cites W2293004735 @default.
- W2808250782 cites W2414378847 @default.
- W2808250782 cites W2471349142 @default.
- W2808250782 cites W2520117834 @default.
- W2808250782 cites W2567922298 @default.
- W2808250782 cites W626980589 @default.
- W2808250782 doi "https://doi.org/10.24963/ijcai.2018/600" @default.
- W2808250782 hasPublicationYear "2018" @default.
- W2808250782 type Work @default.
- W2808250782 sameAs 2808250782 @default.
- W2808250782 citedByCount "3" @default.
- W2808250782 countsByYear W28082507822018 @default.
- W2808250782 countsByYear W28082507822020 @default.
- W2808250782 crossrefType "proceedings-article" @default.
- W2808250782 hasAuthorship W2808250782A5043305308 @default.
- W2808250782 hasAuthorship W2808250782A5046660236 @default.
- W2808250782 hasBestOaLocation W28082507821 @default.
- W2808250782 hasConcept C127413603 @default.
- W2808250782 hasConcept C154945302 @default.
- W2808250782 hasConcept C170154142 @default.
- W2808250782 hasConcept C184337299 @default.
- W2808250782 hasConcept C18555067 @default.
- W2808250782 hasConcept C199360897 @default.
- W2808250782 hasConcept C204321447 @default.
- W2808250782 hasConcept C23123220 @default.
- W2808250782 hasConcept C2776321320 @default.
- W2808250782 hasConcept C2985727698 @default.
- W2808250782 hasConcept C41008148 @default.
- W2808250782 hasConcept C4554734 @default.
- W2808250782 hasConcept C49937458 @default.
- W2808250782 hasConcept C96711827 @default.
- W2808250782 hasConceptScore W2808250782C127413603 @default.
- W2808250782 hasConceptScore W2808250782C154945302 @default.
- W2808250782 hasConceptScore W2808250782C170154142 @default.
- W2808250782 hasConceptScore W2808250782C184337299 @default.
- W2808250782 hasConceptScore W2808250782C18555067 @default.
- W2808250782 hasConceptScore W2808250782C199360897 @default.
- W2808250782 hasConceptScore W2808250782C204321447 @default.
- W2808250782 hasConceptScore W2808250782C23123220 @default.
- W2808250782 hasConceptScore W2808250782C2776321320 @default.
- W2808250782 hasConceptScore W2808250782C2985727698 @default.
- W2808250782 hasConceptScore W2808250782C41008148 @default.
- W2808250782 hasConceptScore W2808250782C4554734 @default.
- W2808250782 hasConceptScore W2808250782C49937458 @default.
- W2808250782 hasConceptScore W2808250782C96711827 @default.
- W2808250782 hasLocation W28082507821 @default.
- W2808250782 hasOpenAccess W2808250782 @default.
- W2808250782 hasPrimaryLocation W28082507821 @default.
- W2808250782 hasRelatedWork W137965669 @default.
- W2808250782 hasRelatedWork W1549203972 @default.
- W2808250782 hasRelatedWork W1568866260 @default.
- W2808250782 hasRelatedWork W2151607039 @default.
- W2808250782 hasRelatedWork W2251013081 @default.
- W2808250782 hasRelatedWork W2472885054 @default.
- W2808250782 hasRelatedWork W2500581104 @default.
- W2808250782 hasRelatedWork W2808250782 @default.
- W2808250782 hasRelatedWork W2999699891 @default.
- W2808250782 hasRelatedWork W3214915308 @default.
- W2808250782 isParatext "false" @default.
- W2808250782 isRetracted "false" @default.
- W2808250782 magId "2808250782" @default.
- W2808250782 workType "article" @default.