Data Portal @ linkeddatafragments.org

Matches in ScholarlyData for { <https://w3id.org/scholarlydata/inproceedings/eswc2015/paper/research/191> ?p ?o. }

• 191 creator genevieve-gorrell.
• 191 creator johann-petrak.
• 191 creator kalina-bontcheva.
• 191 type InProceedings.
• 191 label "LOD-based Disambiguation of Named Entities in @tweets through Context #enrichment".
• 191 sameAs 191.
• 191 abstract "Social media -- and microblogs in particular -- have emerged as high-value, high-volume content, which organisations increasingly wish to analyse automatically. These short, noisy, context-dependent, stylized and dynamic texts currently present a significant challenge for semantic annotation techniques, such as ontology-based named entity disambiguation. State-of-the-art systems, however, have largely ignored the richer, microblog-specific context, which humans draw upon when interpreting these short messages. This paper focuses specifically on quantifying the impact on entity disambiguation performance when readily available contextual information is included from URL content, hash tag definitions, and Twitter user profiles. In particular, including URL content significant improves the performance of a state-of-the-art DBpedia-based entity linking system. Similarly, user profile information for @mentions improves recall by over 10% with no adverse impact on precision. Another contribution lies in a new, publicly available corpus of tweets, which have been hand-annotated with DBpedia URIs, with high inter-annotator agreement.".
• 191 hasAuthorList authorList.
• 191 isPartOf proceedings.
• 191 keyword "Entity linking".
• 191 keyword "Information Extraction for Social Media Mining".
• 191 keyword "Semantic annotation exploiting linked data".
• 191 keyword "entity disambiguation using Linked Open Data".
• 191 keyword "ontology-based information extraction".
• 191 title "LOD-based Disambiguation of Named Entities in @tweets through Context #enrichment".