Text Classification is MeaningCloud's solution for automated document classification. It assigns one or more categories to a text, using standard domain-specific taxonomies (e.g., IPTC. IAB, ICD-10) or user-defined categories. The algorithm combines statistical document classification with rule-based filtering, which allows to obtain a high degree of accuracy and flexibility in a wide range of environments.

Differentiators:

  • Statistical classifiers provide a means to use example documents to define each category.
  • In turn, rule base classifiers helps to fine-tune the classification and correct the output of statistical classifiers.
  • Its powerful rule based classification language is also useful to bootstrap a categorization when no examples are available.
  • Features predefined, standard taxonomies: IPTC, Eurovoc.
  • User can create his/her own categories and classification models.

Important announcement

The new classification models customization console 2.0 and new Text Classification API are now live!

All users with classification models for Text Classification 1.1 are encouraged to upgrade them to the new version before it's deprecated on 15/Sep/2020. Check the migration guide we've published for detailed information.

Documentation

Everything and anything you need to take advantage of this API's full potential.

Test Console

Choose an input and a configuration, and immediately check the results!

Developer Tools

Do you want to integrate this API into your environment? Check our Developer Tools!

Changelog

Version Date Status
2.0 15/Jun/2020

2.0 (15/Jun/2020)

  • Explicit hierarchy can be obtained in the classification for the models where it's defined.
  • Now the abstract of a text can be added as a parameter. The weight derived from terms in it will be three times higher than for those terms found in the text.
  • Improvements have been added to the service that provides the analysis with a double focus: maintaining the performance of the predefined models MeaningCloud provides and improving the performance of large user defined models.
  • Compatibility with models created with Classification Customization Console 2.0.
  • The IAB model has been retired from Text Classification. Now it's served with Deep Categorization.
1.1 06/November/2018

1.1.12 (06/November/2018)

  • New improvements added the IAB model results in English and Spanish.

1.1.11 (26/June/2017)

  • New improvements have been added to the engine for performance and minor bugs have been fixed.

1.1.10 (27/March/2017)

  • General minor bugs fixed in the engine.
  • New improvements have been added to the engine for training performance of large models.
  • New improvements added the IAB model results in English and Spanish.

1.1.9 (27/October/2016)

  • Bug fixed in the categories filter for analyses with IAB.
  • New improvements added the IAB model results in English and Spanish.

1.1.8 (26/April/2016)

  • We have improved the IAB model results in English and Spanish.

1.1.7 (01/December/2015)

  • Improvements in the IAB taxonomy both in English and Spanish.

1.1.6 (06/October/2015)

  • Improvements in the IAB taxonomy both in English and Spanish.
  • Minor bugs have been fixed.

1.1.5 (09/September/2015)

  • Improvements in the results of IPTC in English and Spanish, and IAB, also in English and Spanish.
  • Improvements in the response time for IAB.

1.1.4 (28/July/2015)

  • The IAB model has been improved: a bug in large texts has been fixed and results have been improved.

1.1.3 (14/July/2015)

  • Two new models have been added, the Spanish and English versions of the IAB Taxonomy.

1.1.2 (02/June/2015)

1.1.1 (07/October/2013)

  • The response headers have been updated so the content type is correct for all output formats supported.
  • The documentation has been improved, both in format and contents.
  • Error messages in all APIs have been unified.

1.1 (23/September/2013)

  • New features:
    • The response now contains information regarding the credits consumed by the request and the remaining credits in the status element.
  • The output has been homogenized to follow the new standard for array elements in all APIs.
  • A feedback section has been added to the website.
  • HTTPS support has been added.

Click on the version number to see the changelog.

Languages

  • English
  • Spanish
  • French
  • Italian
  • Portuguese
  • Catalan

Integrations

Related Links

Contact Us

Do you have any questions? Have you detected a bug? Contact us through our feedback section or at support@meaningcloud.com