Connect the dots between the entities in your content with 17 prebuilt targeted extractors
Overview
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
How it Works
Process
Building on the results of entity extraction and linking, Rosette relationship extraction identifies how different entities are related to each other using a multistep process:
- Performs deep syntactic parsing of the sentence and identifies dependencies between words
- Resolves the entities using entity extraction and entity linking for disambiguation
- Identifies relationships using a deep convolutional neural network
- Classifies them using patterns that were induced from external sources such as Wikidata
Tech Specs
Availability and platform support
| Deployment availability: | |
| Bindings: |
Supported Languages
English only
Targeted organizational relationships
| Founded by | Headquartered at | Top employee of | |
| Acquired by | Provider to | Partner of | |
| Collaborator with | Subsidiary of | Employee of |
Targeted personal relationships
| Location born at | Family member of | Sibling of | |
| Married to | Parent of | Educated at | |
| Resident of | Citizen of |
{
"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"
}
]
}
Try the Demo
Deployment
Rosette Cloud
Sign up today for a free 30-day trial
The SaaS version of Rosette is rapidly implemented, low maintenance and ideal for users who wish to pay based on monthly call volume. Numerous bindings through a RESTful API are supported.
Rosette Server Edition
This on-premise private cloud deployment puts all the functionality of Rosette Cloud behind your secure firewall, and enables advanced user settings, access to custom profiles (user-specific configuration setups), and deployment of custom models.
Rosette Java Edition
For on-premise systems that need the low-latency, high-speed integration of an SDK, Rosette Java is the way to go. It has been deployed in the most demanding, high-transaction environments, including web search engines, financial compliance, and border security.
Rosette Plugins
Just plug in Rosette for instant high-accuracy multilingual search and fuzzy name search for Elasticsearch or Apache Solr.
Quality documentation and support
Our support team responds to customers in less than a business day, and is committed to a satisfactory resolution. Users have access to in-depth documentation describing all the features, with code examples and a searchable knowledge base.
Visit our GitHub for bindings and documentation.
Questions?
Email: info@basistech.com
Phone: +1-617-386-2000
Select Rosette Customers
Deep Search for Salesforce
AI-driven Search Application for Salesforce
KonaSearch is a best-in-class search application for Salesforce enabling users to search every field, file, and object across multiple orgs and other data sources.
