The Non-Technical Guide to Popular Conversational AI Terminology

We talk about Conversational AI a lot on our website and blog, after all this technology is at the core of what we do at The Bot Forge. You may well have encountered some of the different terminology used. But what do developers and technologists really mean when they use these terms?

1. Algorithm

An algorithm functions as a step-by-step procedure for calculations. These formulas enable automated processing and form the foundation for artificial intelligence technology.

2. Artificial Neural Network

Artificial Neural Networks replicate biological brain networks and represent a machine learning category. Though less powerful than human brains, they handle complex tasks like chess-playing systems such as AlphaZero.

3. Artificial Intelligence

AI research and development aims to enable computers to make decisions and solve problems. This computer science field encompasses three main distinctions of intelligence.

4. Big Data

Big data encompasses the large volume of data -- both structured and unstructured -- that floods through a business daily. Within AI contexts, this data serves as fuel which is processed to provide inputs for surfacing patterns and making predictions.

5. Chatbots

A chatbot is a conversational interface powered by AI and specifically NLP. These systems function as text-based applications within platforms like Facebook Messenger or employ voice-enabled technology similar to Amazon Alexa.

6. Cognitive

Cognitive computing mimics human brain thinking through machine learning techniques. As researchers approach transformative artificial intelligence, cognitive applications gain increasing relevance.

7. Conversational Design / Conversational Designer

This emerging role combines knowledge of UX design, psychology, audio design, linguistics, and copywriting. Practitioners create natural conversations ensuring quality user experiences through understanding how computers should communicate humanly.

8. Deep Learning

Also termed deep neural networks, deep learning uses algorithms to understand data and datasets. This machine learning subfield employs algorithms inspired by brain structure and neural networks, becoming popular for solving traditional Natural Language Processing challenges like sentiment analysis.

9. Entity and Entity Extraction

Entities (sometimes called slots) extract parameter values from natural language inputs. Entity extraction techniques are used to identify and extract different entities through regex, dictionary, pattern-based, or statistical methods -- for example, extracting colour names, product types, or location data from conversations.

10. Intelligent Personal Assistants

This term describes voice-activated assistants which perform tasks for us, including Amazon Alexa, Google Assistant, and Siri, as opposed to text-based chatbot alternatives.

11. Intent

An intent establishes a mapping between what a user says and what action should be taken by your chatbot. Naming conventions typically reflect completed actions (FindProductInformation, ReportHardWareProblem, FundraisingEnquiry).

12. Machine Learning

Machine Learning or ML for short is probably used by you every day in Google search for example or Facebook's image recognition. ML enables software to accurately predict outcomes without explicit programming through statistical analysis of input data.

13. Natural Language Processing

Natural language processing (NLP) is broadly defined as the automatic manipulation of natural language, like speech and text, by software. This AI branch helps computers understand, interpret, and manipulate human language by drawing from computer science and computational linguistics disciplines.

14. Natural Language Understanding

This subfield of NLP called natural language understanding (NLU) has begun to rise in popularity. NLU transcends structural language understanding to interpret intent, resolve context and word ambiguity, and generate well-formed human language. NLU algorithms tackle the extremely complex problem of semantic interpretation, enabling more natural conversations.

15. Sentiment Analysis

Sentiment analysis determines whether a piece of writing is positive, negative or neutral, with advanced approaches identifying emotional states like anger, sadness, and happiness.

16. Utterance

An utterance represents anything the user says via text or speech. The complete sentence constitutes the utterance -- for instance, "what is my favourite colour" in its entirety.

17. Conversational IVR

Conversational IVR represents a software system which uses voice commands from customers. Unlike traditional IVR systems requiring simple voice commands ("yes" or "no"), conversational versions enable natural language understanding, allowing callers to describe questions or concerns in their own words which is then matched to an intent by natural language understanding.