Tagmatic
Tagmatic is a Machine Learning SaaS platform for sophisticated text classification that works with dictionaries, taxonomies, vocabularies and knowledge graphs. Language agnostic, it works out of the box and trains on the fly. It includes services for Text Classification, Named Entity Recognition and Entity Relationship Prediction.
Features
- Tagmatic is a sophisticated content classification SaaS product
- It uses machine learning to classify and tag content
- It classifies content using your own vocabularies and dictionaries
- It is language agnostic
Benefits
- It is trivially easy to integrate into your systems
- It self-optimises and learns on-the-fly independently to your workflow
- It dramatically reduces the time, cost and complexity of tagging
- It solves the AI scaling and engineering challenges
Pricing
£3,000 a licence a month
- Free trial available
Service documents
Request an accessible format
Framework
G-Cloud 13
Service ID
5 3 3 9 1 9 2 3 2 2 2 4 1 8 6
Contact
datalanguage
Paul Wilton
Telephone: 0794 222 3149
Email: paul.wilton@datalanguage.com
Service scope
- Software add-on or extension
- No
- Cloud deployment model
- Public cloud
- Service constraints
- No
- System requirements
-
- Clients needs to HTTPS access to the public internet
- Requires an standards-compliant HTTP client library for access
User support
- Email or online ticketing support
- Email or online ticketing
- Support response times
- During UK office hours we use all reasonable effort and commercial endeavours to rectify the fault(s) within 3 hours from the time of notification, and outside of such hours use reasonable endeavours to rectify the fault(s) as soon as is reasonably practicable.
- User can manage status and priority of support tickets
- No
- Phone support
- No
- Web chat support
- No
- Onsite support
- Yes, at extra cost
- Support levels
- Tagmatic is a self-service SaaS product. We can supply additional onsite training and support via our professional services team
- Support available to third parties
- No
Onboarding and offboarding
- Getting started
- User documentation
- Service documentation
- Yes
- Documentation formats
- HTML
- End-of-contract data extraction
- Any training data that is uploaded by users is destroyed after contract end.
- End-of-contract process
- At the end of the contract, access to the user's SaaS product account is removed, training data is deleted and then the account is deleted.
Using the service
- Web browser interface
- No
- Application to install
- No
- Designed for use on mobile devices
- Yes
- Differences between the mobile and desktop service
- The product is a cloud-hosted SaaS API that can be accessed from both mobile and desktop
- Service interface
- No
- User support accessibility
- WCAG 2.1 A
- API
- Yes
- What users can and can't do using the API
- They can train the machine learning models via a /train endpoint and then perform predictions based on that training via a /predict endpoint.
- API documentation
- Yes
- API documentation formats
- Open API (also known as Swagger)
- API sandbox or test environment
- Yes
- Customisation available
- Yes
- Description of customisation
- The predictive models are customised to predict against the customers own content via the model training process.
Scaling
- Independence of resources
- Each tenancy is fully isolated in the cloud, both in terms of compute and data.
Analytics
- Service usage metrics
- Yes
- Metrics types
- The following metrics are available via the API: Precision, Recall, F1 score, Current Size of Dynamic Training Data Corpus, Number of Classifiers (self-optimising)
- Reporting types
- API access
Resellers
- Supplier type
- Not a reseller
Staff security
- Staff security clearance
- Other security clearance
- Government security clearance
- Up to Security Clearance (SC)
Asset protection
- Knowledge of data storage and processing locations
- Yes
- Data storage and processing locations
-
- United Kingdom
- European Economic Area (EEA)
- User control over data storage and processing locations
- No
- Datacentre security standards
- Managed by a third party
- Penetration testing frequency
- At least once a year
- Penetration testing approach
- In-house
- Protecting data at rest
- Physical access control, complying with another standard
- Data sanitisation process
- Yes
- Data sanitisation type
- Deleted data can’t be directly accessed
- Equipment disposal approach
- A third-party destruction service
Data importing and exporting
- Data export approach
- There is no user data stored in the platform.
- Data export formats
- Other
- Other data export formats
- N/a
- Data import formats
- Other
- Other data import formats
- N/a
Data-in-transit protection
- Data protection between buyer and supplier networks
- TLS (version 1.2 or above)
- Data protection within supplier network
- TLS (version 1.2 or above)
Availability and resilience
- Guaranteed availability
- Under review currently.
- Approach to resilience
- Tagmatic is deployed in the cloud with all data replicated across multiple availability zones.
- Outage reporting
- Email alerting
Identity and authentication
- User authentication needed
- Yes
- User authentication
- Identity federation with existing provider (for example Google Apps)
- Access restrictions in management interfaces and support channels
- Each tenancy is completely isolated in the cloud. We provide no variation in authorisation levels within the scope of each tenancy.
- Access restriction testing frequency
- At least once a year
- Management access authentication
- Identity federation with existing provider (for example Google Apps)
Audit information for users
- Access to user activity audit information
- Users have access to real-time audit information
- How long user audit data is stored for
- User-defined
- Access to supplier activity audit information
- No audit information available
- How long system logs are stored for
- Between 1 month and 6 months
Standards and certifications
- ISO/IEC 27001 certification
- No
- ISO 28000:2007 certification
- No
- CSA STAR certification
- No
- PCI certification
- No
- Cyber essentials
- Yes
- Cyber essentials plus
- No
- Other security certifications
- No
Security governance
- Named board-level person responsible for service security
- Yes
- Security governance certified
- No
- Security governance approach
- Security governance is managed under the remit of our internal Data Governance Policies and Procedures framework. As a stateless SaaS product, Tagmatic falls into the lowest risk category.
- Information security policies and processes
- Information security governance is managed under the remit of our internal Data Governance Policies and Procedures framework. As a stateless SaaS product, Tagmatic falls into the lowest risk category.
Operational security
- Configuration and change management standard
- Supplier-defined controls
- Configuration and change management approach
- We have a fully automated continuous delivery operating model, but none of this is ever exposed to any customer. Our services are subject to regular internal security audits.
- Vulnerability management type
- Supplier-defined controls
- Vulnerability management approach
- We use consequence scanning and value stream mapping vulnerability analysis to identify risks, and anomaly detection in our usage analytics to detect exploits. Issues are triaged and then prioritised into our continuous delivery pipeline.
- Protective monitoring type
- Undisclosed
- Protective monitoring approach
- We have full monitoring on Tagmatic, with events used to generate anomaly-triggered alerts. Alerts are investigated immediately.
- Incident management type
- Undisclosed
- Incident management approach
- Users report incidents via our support email. We don't provide tailored incident reporting, but share general status updates about any ongoing issues transparently over email with all impacted users.
Secure development
- Approach to secure software development best practice
- Supplier-defined process
Public sector networks
- Connection to public sector networks
- No
Social Value
- Fighting climate change
-
Fighting climate change
Tagmatic is a domain-agnostic machine learning platform which can be used to annotate climate change scientific evidence with structured metadata, enabling very large repositories to be queried with highly complex and precise semantic queries - greatly improving the Findability, Interoperability (via the use of public domain semantic identifiers) and Resusability of relevant data. - Covid-19 recovery
-
Covid-19 recovery
Tagmatic is a domain-agnostic machine learning platform which can be used to annotate clinical evidence with structured metadata, enabling very large data registries to be queried with highly complex and precise semantic queries - greatly improving the Findability, Interoperability (via the use of public domain semantic identifiers) and Resusability of relevant data.
Pricing
- Price
- £3,000 a licence a month
- Discount for educational organisations
- No
- Free trial available
- Yes
- Description of free trial
- We offer a fully functional 30-day free trial