Tag Archives: text annotation

Building bot-ready knowledge bases #1: Introduction

This post is part of a series. For more information and links to other posts in the series, see the “Building bot-ready knowledge bases” home page.

Structured writing and AI technologies: A synergistic solution

Benefits of structured writing

During our years working together on technical and scientific communication projects, Dick and I have created many structured writing solutions and training packages for software providers and educational institutions based on technologies like DITA/XML (Darwin Information Typing Architecture), DocBook, and Markdown.

We believe that the extra care that goes into structured knowledge bases benefits both the creators and users of the information.

Benefits of AI-based information delivery systems

Over the past year we have immersed ourselves in AI technology, Anna as a linguistic analyst and text annotator and Dick as an avid machine learning and data science student and practitioner.

We have come to greatly appreciate the benefits of an AI-based information delivery system to both users and owners of knowledge bases.

Possibilities for synergistic solutions that combine both techniques

Based on our years of structured writing experience and our newly-developed knowledge of the AI world, we have concluded that combining traditional structured writing strategies with the latest AI tools and techniques can  provide a more powerful, cost-effective, and user-friendly KB solution than either strategy can offer on its own.

Prototyping bot-ready information solutions

To illustrate how such synergistic solutions can work, and the possible benefits they can provide, we have reworked various structured documentation projects we have written in the past, and repurposed them in a machine learning (ML)- and natural language processing (NLP)-based environment.

For example, when we wrote the “DITAinformationcenter” educational material that we invented for prototyping purposes, we created two sets of short, non-technical, structured documentation sets called “Grocery Shopping” and “Cleaning the Garage.”

Image from "cleaning the garage" docset
Image from “cleaning the garage” docset

We started our current “bot-ready” initiative by pairing the two docsets with Dialogflow, a Google-owned chatbot that is based on machine learning and natural-language conversations.

Dialogflow can be used to create conversational interfaces for websites and messaging platforms, and it is free for small prototypes, such as ours. Beyond the prototype stage, it can scale to handle larger chatbot applications.

We plan to include as part of this initiative other existing information projects like Drupal API documentation, scientific articles, and even personal projects like Dick’s “High-tech adventure” (published as blogs on this site).

Goal of our “bot-ready” initiative

Our goal for this initiative is to inspire owners and developers of technical and scientific documentation to try a new, “traditionally modern” way to improve the quality and efficiency of both their knowledge base content and the AI-based delivery system that provides the information to their users.

What’s next?

Over a period of several months, as we develop various AI-based KB prototypes, we will be blogging our experiences, tips, and techniques on this site.

Our next post will be a description of our “grocery shopping” project and docset.