@prefix foaf: . @prefix ns1: . @prefix ns2: . ns1:maria-koutraki foaf:made ns2:iswc-2017-iswc-2017-posters-and-demos-632 . ns1:harald-sack foaf:made ns2:iswc-2017-iswc-2017-posters-and-demos-632 . ns1:jorg-waitelonis foaf:made ns2:iswc-2017-iswc-2017-posters-and-demos-632 . @prefix ns3: . @prefix ns4: . ns4:proceedings ns3:hasPart ns2:iswc-2017-iswc-2017-posters-and-demos-632 . @prefix rdf: . @prefix ns6: . ns2:iswc-2017-iswc-2017-posters-and-demos-632 rdf:type ns6:SocialObject , ns3:InProceedings , ns6:InformationObject , ns6:Object . @prefix rdfs: . ns2:iswc-2017-iswc-2017-posters-and-demos-632 rdf:type rdfs:Resource . @prefix ns8: . ns2:iswc-2017-iswc-2017-posters-and-demos-632 rdf:type ns8:ProceedingsPaper . @prefix owl: . ns2:iswc-2017-iswc-2017-posters-and-demos-632 rdf:type owl:Thing ; rdfs:label "Entity Suggestion Ranking via Context Hashing" . @prefix ns10: . ns2:iswc-2017-iswc-2017-posters-and-demos-632 owl:sameAs ns10:iswc-2017-iswc-2017-posters-and-demos-632 . @prefix ns11: . ns2:iswc-2017-iswc-2017-posters-and-demos-632 ns11:abstract "In text-based semantic analysis the task of named entity linking (NEL) establishes the fundamental link between unstructured data elements and knowledge\nbase entities. The increasing number of applications complementing web data\nvia knowledge base entities has led to a rich toolset of NEL frameworks [4,7]. To\nresolve linguistic ambiguities, NEL relates available context information via statistical analysis, as e.g. term co-occurrences in large text corpora, or graph analysis, as e.g. connected component analysis on the contextually induced knowledge\nsubgraph. The semantic document annotation achieved via NEL algorithms can\nfurthermore be complemented, upgraded or even substituted via manual annotation, as e.g. in [5]. For this manual annotation task, a popular approach suggests\na set of potential entity candidates that fit to the text fragment selected by the\nuser, who decides about the correct entity for the annotation. The high degree\nof natural language ambiguity causes the creation of a huge sets of entity candidates to be scanned and evaluated. To speed up this process and to enhance\nits usability, we propose a pre-ordering of the entity candidates set for a predefined context. The complex process of NEL context analysis often is too time\nconsuming to be applied in an online environment. Thus, we propose to speed\nup the context computation via approximation based on the offline generation\nof context weight vectors. For each entity, a context vector is computed before-\nhand and is applied like a hash for quickly computing the most likely entity\ncandidates with respect to a given context. In this paper, the process of entity\nhashing via context weight vectors is introduced. Context evaluation via weight\nvectors is evaluated on the test case of SciHi 1 , a web blog on the history of\nscience providing blog posts semantically annotated with DBpedia entities." . @prefix dc: . ns2:iswc-2017-iswc-2017-posters-and-demos-632 dc:creator ns1:jorg-waitelonis , ns1:harald-sack , ns1:maria-koutraki , ns1:rima-turker . @prefix xsd: . ns2:iswc-2017-iswc-2017-posters-and-demos-632 dc:subject "semantic annotation"^^xsd:string , "link graph analysis"^^xsd:string , "entity ranking"^^xsd:string ; dc:title "Entity Suggestion Ranking via Context Hashing" . @prefix ns14: . @prefix ns15: . ns2:iswc-2017-iswc-2017-posters-and-demos-632 ns14:authorList ns15:iswc-2017-iswc-2017-posters-and-demos-632 ; foaf:maker ns1:rima-turker , ns1:harald-sack , ns1:maria-koutraki , ns1:jorg-waitelonis ; ns3:abstract "In text-based semantic analysis the task of named entity linking (NEL) establishes the fundamental link between unstructured data elements and knowledge\nbase entities. The increasing number of applications complementing web data\nvia knowledge base entities has led to a rich toolset of NEL frameworks [4,7]. To\nresolve linguistic ambiguities, NEL relates available context information via statistical analysis, as e.g. term co-occurrences in large text corpora, or graph analysis, as e.g. connected component analysis on the contextually induced knowledge\nsubgraph. The semantic document annotation achieved via NEL algorithms can\nfurthermore be complemented, upgraded or even substituted via manual annotation, as e.g. in [5]. For this manual annotation task, a popular approach suggests\na set of potential entity candidates that fit to the text fragment selected by the\nuser, who decides about the correct entity for the annotation. The high degree\nof natural language ambiguity causes the creation of a huge sets of entity candidates to be scanned and evaluated. To speed up this process and to enhance\nits usability, we propose a pre-ordering of the entity candidates set for a predefined context. The complex process of NEL context analysis often is too time\nconsuming to be applied in an online environment. Thus, we propose to speed\nup the context computation via approximation based on the offline generation\nof context weight vectors. For each entity, a context vector is computed before-\nhand and is applied like a hash for quickly computing the most likely entity\ncandidates with respect to a given context. In this paper, the process of entity\nhashing via context weight vectors is introduced. Context evaluation via weight\nvectors is evaluated on the test case of SciHi 1 , a web blog on the history of\nscience providing blog posts semantically annotated with DBpedia entities." ; ns3:hasAuthorList ns15:iswc-2017-iswc-2017-posters-and-demos-632 ; ns3:isPartOf ns4:proceedings ; ns3:keyword "link graph analysis"^^xsd:string , "semantic annotation"^^xsd:string , "entity ranking"^^xsd:string ; ns3:title "Entity Suggestion Ranking via Context Hashing" . ns1:rima-turker foaf:made ns2:iswc-2017-iswc-2017-posters-and-demos-632 .