Finto AI is a service for automated subject indexing. The last part of its punny name, AI, actually refers to automated indexing. Finto AI can be used to index text in three languages: Finnish, Swedish and English. It currently gives suggestions based on the General Finnish Ontology.
Web Interface
You can use the form by copy-pasting text on the appropriate field and then clicking the button for results. In the drop-down menu you can choose the language and analysis method for the text. You can also set the maximum number of suggestions you would like to receive.
REST-style API
Finto AI can be used via the form at ai.finto.fi or API. A more detailed description of the API can be found in this OpenAPI/Swagger documentation, you can also read more from this wiki.
An API integration is already in place at the University of Jyväskylä : students submitting their MA thesis to the JYX repository get suggestions from Annif that they can use or discard, then a librarian/informatician does a final check.
Vocabularies and Languages
Finto AI currently uses the latest version of the General Finnish Ontology (2020.4 Diotima) including placenames (YSO Places). It supports three languages, Finnish, Swedish and English, and gives suggestions in the same language as the text it is given. In the development process of Annif we have discovered and tested several algorithms, and selected the currently best combination for Finto AI. The ensemble model based on neural networks has been trained with data from Finna discovery service. The development work of Annif is ongoing and we will offer updates and improvements to Finto AI accordingly.
From Annif API to Finto AI, the Production Version
Finto AI is based on Annif, a tool for automated subject indexing. You can read more about using Annif in it's GitHub Wiki. To work, Annif needs a controlled vocabulary (subject headings, thesaurus or classification) and existing metadata - Annif can then be used to assign subjects for new documents. This tool is built upon a combination of existing natural language processing and machine learning tools including Maui, Omikuji, fastText and Gensim. It is designed to be multilingual and it can support any subject vocabulary (in SKOS or a simple TSV format). It can be used either via a command-line interface or a microservice-style REST API. In fact, this demo demo API under Api.annif.org and the demo form at annif.org are the basis of Finto AI. As a development tool, Annif offers more methods than Finto AI, successful features will be integrated to Finto AI in time.
Future developments
In the near future, after some further research and development, we’ll aim to offer a learn method via the API, so that human-corrected results could be used to teach Annif and improve results.
