Search the Findwise web

Transform your documents into an asset – instead of a burden

How to use AI to automate translation and perform metadata extraction on documents


In the world of Information Technology, change is a natural and frequent occurrence. As companies increase their investments in new communication channels, such as social media or chatbots, an enormous amount of knowledge gets stored in an ever increasing number of documents.

In companies that operates domestically, these documents are often in a single language. However for companies with offices around the globe, their documents can be written in several languages. For such companies, translation issues becomes an issued and adds to the complexity for their database.

One way to address such language complexity is to have a “corporate language”. However, when information is supposed to be used by customers in a specific country, it is often necessary to use the native language - and language complexity is again and issue for the company. If one factors in all the marketing material, installation manuals, spare part specifications, instructions, policies etc., the costs and effort to the company to publish and maintain such a complex database becomes enormous.


We have used an Artificial Intelligence (AI) to automate the process of translation and to perform automatic metadata extraction on documents.
(The picture below shows an overview of the solution)

An AI solution has two major benefits:

1, The process of translation itself is greatly improved by adding corporate “terms and phrases”, which reduces duplication in translation and ensures that the correct name is used throughout the organisation..

2, A solid foundation for fast and efficient search solutions is created by adding of metadata to each document. This makes it possible to actually “find what you are looking for” quickly and accurately. While such work can be done manually by users, it has already been tried many, many times before and with limited results. When an AI can identify and add correct metadata to a unique document, the resulting user and search experience is impressive.

Some of the features included in the solution are:

  • Automatic translation of a document to English or any language selected
  • Ability to select and translate one, or many documents, to multiple languages
  • Custom translation dictionary for hermetic and specific names
  • Metadata extraction based on document structure and content – we separate structure and content making it possible to keep the structure of a document
  • Metadata extraction model (or models) – which makes it possible to customize and select which metadata that are extracted
  • Search interface with filters
  • A Teams chatbot understanding user´s natural language making it possible to ask the bot (another way of searching) for the right document in your own, local, language

The solution is built on Microsoft Office 365/SharePoint Online and Microsoft Azure platform using many different “products” such as SharePoint Online, Microsoft Flow, Azure Cognitive Services, Azure Bot Framework and Microsoft Teams. The solution is customisable and accessible on various devices (i.e. phones, tablets, PCs).


A solution like this can have a positive impact on many different levels and processes within an organisation. Our focus has been to create the following business values::

  • Time and cost savings: Automatisation of every day processes
  • Higher quality of services: Reuse of translations and common language
  • Information as an asset: people find what they are looking for, in their native tongue

Technologies used on Transform your documents into an asset – instead of a burden

We build search solutions based on any platform and have partnerships with all leading vendors.

Microsoft SharePoint & Office 365 - Search in SharePoint and Office 365 is more powerful than ever before