Conversational AI
Glossary

Get acquainted with key terms in the fields of conversational AI,

computational linguistics, large language models, and digital customer experience.

Term of the Week

Term of the Week

Adaptive Communications
Adaptive Communications

Adaptive Communications ensures easy bi-directional communication, through text, touch and voice capabilities, between its clients and their end-users

Read more

A

Adaptive Communications

Adaptive Communications ensures easy bi-directional communication, through text, touch and voice capabilities, between its clients and their end-users

 Agent Handover

An agent handover occurs when a request made by a user is too specific for a Chatbot to handle. When this happens, the chatbot then offers the user the option to be forwarded to a human agent, who can then seize the conversation and assist the customer manually.

 Application Programming Interface (API)

An application programming interface, otherwise known as an API, is a software that operates as an intermediary between two applications to enable them to communicate with one another. Whenever you use WhatsApp, Facebook or search for something on your phone, you’re using an API.

 Automatic Speech Recognition (ASR)

Automatic Speech Recognition (ASR), also known as speech-to-text (STT), is a versatile subfield of computational linguistics that configures technologies that enable computers to recognize and convert natural spoken language into text. 

 Average Handle Time (AHT)

Average Handle Time (AHT) is a key performance indicator (KPI) used by call center executives to measure the efficiency and productivity of their customer service teams. 

 Average Hold Time (AHT)

What Is Average Hold Time (AHT)? Average Hold Time (AHT) is a metric used in call center operations to measure the average time a customer spends on hold during a call. It is calculated by dividing the total time customers spend on hold by the total number of calls handled by the call center during a

C

Chatbot

A chatbot, short for chatterbot, is an artificial intelligence (AI) application that generates dialogue by mimicking human language based interactions through voice commands, text commands, or both. 

 Computational Linguistics

Computational linguistics is the scientific discipline which deals with the computational modelling of natural language (both in written and spoken form). Computational linguistics draws from a variety of different fields, including linguistics, artificial intelligence, cognitive science, and so on, to facilitate human interactions with machines by allowing them to gain a computational understanding of language. 

 Context Switching in Chatbots

Context switching in chatbots is similar to that which is found between humans throughout conversations. It occurs when we speak about one topic and then switch to another mid-conversation. For example, when speaking about the weather with a friend, you might quickly jump to the topic of scheduling plans for the weekend. 

 Conversational AI

Conversational AI is a combination of technologies, such as chatbots and voice assistants, that users can communicate with to receive assistance. An effective conversational AI application combines machine learning, natural language processing (NLP), and sometimes even IVR and ASR to achieve the most human-like interaction possible. 

 Conversational Process Automation (CPA)

Conversational Process Automation (CPA) uses artificial intelligence to bridge the gap between the customer facing world and process automation systems. CPAs are quite special because they automate both conversations and processes.

 Conversational UI

A conversational user interface (CUI) is essentially a user interface designed for computers in order to imitate a conversation with a human. This sort of interface allows for people to “communicate” with a computer in their natural language instead of through syntax-specific commands. Prior to conversational user interfaces, graphical user interfaces (GUIs) were used in order to translate an action into a format the computer would understand by presenting the user with a graphical interface he can interact with using a keyboard and a mouse, such as pressing on a “return” icon to go back to the previous page.

 Conversational User Experience (CUX)

Conversational user experience (CUX) is a human-like conversational interaction between people and computers in either text (chatbot) or voice form. CUX is aimed at providing users with a more personalized interaction by lessening the robotic feeling computers tend to emit. CUX does this by understanding a user’s intent by using artificial intelligence models such as natural language processing.

D

Dialogue Manager (DM)

A dialogue manager (DM) is the central component of a spoken dialogue system and is responsible for the state, as well as the flow, of the conversation. Though there are many types of DM that fulfil different roles, one thing every DM has in common is that they are stateful. 

F

Functional Programming

What is Functional Programming? Functional programming, also known as FP, is the process of using pure functions to build a software which helps to avoid the use of mutable data and side-effects.  Functional programming is declarative, meaning it expresses the logic of the computation without explicitly outlining its control flow.  The overriding difference between other programming paradigms

G

Google Bard

Bard is a cutting-edge conversational AI technology developed by Google that leverages the company's Language Model for Dialogue Applications (LaMDA). 

 GPT-3

Released in mid 2020, GPT-3, or Generative Pretrained Transformer 3, is OpenAI’s third generation language prediction model within their GPT-n series. The tool uses pre-trained algorithms and deep learning in order to generate human-like text. GPT-3 algorithms were fed an exuberant amount of data, 570GB to be exact, by using a plethora of OpenAI texts, something called CommonCrawl (a dataset created by crawling the internet). GPT-3’s capacity exceeds that of Microsoft’s Turing NLG ten times over and it’s known to be the largest existing neural network model existing to date. 

I

Interactive Voice Response – IVR

Interactive voice response (IVR) systems are automated voice responses interacting with a user. A caller typically engages with an IVR system by listening to a menu and responding by selecting a number on his phone to trigger a series of appropriate systemic responses. 

K

Knowledge Graph

A knowledge graph (KG) organizes data from various sources, gets information on entities in a specific domain (e.g., people or places), and creates connections between them in order for the data to be made understandable by the computer. The machine then retains this information as knowledge, using it at different times and in a variety of different circumstances.

M

Machine Learning (ML)

Machine Learning (ML) is a method stemming from a branch within artificial intelligence that enables machines to make decisions or predictions based on data rather than a predefined algorithm. A widely known example of applied machine learning is Gmail Inbox's Smart Reply system, assisting people by automating 10% of their email responses.It is based on the foundation that systems can automatically learn from sample data sets (known as "training data") to characterize patterns that help create predictions and fashioning decisions with minimal human intervention.

N

Named-entity Recognition (NER)

Named-entity Recognition (NER) is a method of recognizing and classifying essential pieces of information from within larger unstructured text-based data into predefined categories such as person names, organizations, locations and more.

 Natural Language Generation (NLG)

What is Natural Language Generation? Natural language generation (NLG) is a subsection within Natural Language Processing (NLP), the border domain that encompasses all software in charge of interpreting and generating human language.  NLG is the domain responsible for converting structured data into meaningful phrases in the form of natural language. It can communicate narratives in a human-like manner at

 Natural Language Processing (NLP)

Natural language processing (NLP) is a branch of technology that handles the interactions between natural human languages and machines. Natural language processing uses a combination of computational linguistics, machine learning, and deep learning models to train machines to understand speech and respond in much the same way as human beings would. In other words, the system can process and fully understand the input language (whether it be in text or voice format) and respond in a meaningful way by comprehending the writer’s intent and sentiment. 

 Natural Language Understanding (NLU)

Natural Language Understanding (NLU) is a branch of Natural Language Processing (NLP) that enables computers to understand the meaning of texts. In other words, it’s the process of transforming human language into a format understandable by machines. Once the meaning of a text is understood, computers can interact more naturally with its users, boosting the overall experience.

R

Robotic Process Automation (RPA)

Robotic Process Automation (RPA), also known as software robotics, refers to a technology that automates repetitive, rule-based digital tasks such as re-entering data, copying, pasting, etc. Traditionally, another form of process automation was more commonly used, namely, business process automations (BPAs). This software is geared to automate routine business tasks and requires a software developer to produce a list of actions into the back-end system in order to automate a specific task. 

T

Turing Test

Coined after the British polymath, Alan Turing, in 1950, the Turing test was initially designed as a basic way to examine a computer’s ability to show intelligence indistinguishable from that of a human. Now, however, the test has become a staple within the world of Artificial Intelligence. 

 Twilio

What is Twilio? Twilio is an American cloud communications platform known for its Customer Engagement Platform (a developer platform for communications) and its application program interfaces (APIs) (a programmable set of tools developers can use to construct the customer experience they want).   Developers can construct an omni-channel digital engagement experience with the Twilio Customer Engagement Platform including Whatsapp, SMS, Video, Email, and

V

Voice Assistant (VA)

Voice Assistants (VA) are a combination of technologies that include natural language processing (NLP), voice recognition, and voice synthesis to communicate with its users using natural language. Voice assistants are commonly confused with virtual assistants, an umbrella term encompassing various types of agents that perform different tasks and individual services. Although virtual assistants can perform similar tasks, they are not entirely synonymous with one another.

W

Web Scraping

Web Scraping deals with the extraction of specific data from a website. Though web scraping can be done manually, it is usually carried out using a bot or web crawler to fetch the information, export it and present it to the user in a format that is easier to digest and manage, whether it’s in a spreadsheet or an API.

 What Is Functional Programming?

Functional programming, also known as FP, is the process of using pure functions to build a software which helps to avoid the use of mutable data and side-effects. Functional programming is declarative, meaning it expresses the logic of the computation without explicitly outlining its control flow.
Group 3462 555 1
Group 12 1

The best of conversational technologies,
delivered weekly.