French Semantic Metadata: Entity Relevance Score

The relevance capability detects the importance of each unique entity and assigns a relevance score in the range 0-1 (1 being the most relevant and important). The score has 3-digit precision after the decimal point.

The relevance scoring takes into account the disambiguation of companies and geographies so that each unique entity will get a single relevance score, even if it is referenced in various ways throughout the text.

By default, Entity Relevance is turned on, but it can be turned off by configuring the calculateRelevanceScore parameter in paramsXML.

Entity relevance scores are comparable across input texts. This means that you can use entity relevance scores in order to determine entity relevance at a collection level, not just at a document level.

Example of Relevance results in RDF output:

<rdf:Description rdf:about="http://d.opencalais.com/dochash-1/1a4a-35f6-957f-823/Relevance/2"
 <rdf:type rdf:resource=http://s.opencalais.com/1/type/sys/RelevanceInfo />
 <c:docId rdf:resource="http://d.opencalais.com/dochash-1/1a4a-35f6-957f-823" />
 <c:subject rdf:resource="http://d.opencalais.com/comphash-1/d82b-5256-3277-b376"/>
 <c:relevance>0.655</c:relevance>
</rdf:Description>

Example of Relevance results in Simple Format output:

<Country count="1" relevance="0.180">États-Unis</Country>
<Person count="1" relevance="0.330">Nicolas Sarkozy</Person>
<ProvinceOrState count="1" relevance="0.180" normalized="Bretagne,France">Bretagne</ProvinceOrState>