What is relationship extraction?

Relationships are the grammatical and semantic connections between two entities in a piece of text. Rosette® uses a combination of deep learning and semantic rules to recognize and extract the relationship that connects the entities.

Adaptability

Rosette relationship extraction includes 17 prebuilt targeted extractors. that recognize a pretrained selection of relationship types (such as “acquired by” and “subsidiary of”). These are especially useful in commerce and intelligence applications. With on-premise Rosette deployments, you can create your own targeted extractor to find documents mentioning people, locations, and organizations that share the particular relationships you seek.

Product highlights

• 17 targeted extractors
• English only
• Fast and scalable
• Industrial-strength support
• Constantly stress-tested and improved
• Cloud and on-premise deployments

Targeted organizational relationships

Targeted personal relationships

{
  "relationships": [
    {
      "predicate": "Organization Headquarters",
      "predicateId": "ORG-HEADQUARTERS",
      "arg1": "FLIR Systems",
      "arg1Id": "Q5426537",
      "arg2": "Oregon",
      "arg2Id": "Q824"
    },
    {
      "predicate": "Person Employee or Member of",
      "predicateId": "PER-EMPLOYEE-MEMBER-OF",
      "arg1": "Timms",
      "arg2": "FLIR"
    },
    {
      "predicate": "Organization top employees",
      "predicateId": "ORG-TOP-EMPLOYEES",
      "arg1": "FLIR",
      "arg2": "Timms"
    }
  ]
}