Glossary

A

API: An API, or Application Programming Interface, is a set of definitions, protocols, and tools for building application software. It helps developers by essentially providing the building blocks for a program.
AI: Artificial Intelligence (AI) technology aims to create or simulate, in robots or software, intelligence comparable to human. These processes include learning, which is the acquisition of information and rules, then reasoning, which is using the rules to reach approximate or definite conclusions, and eventually, self-correction.
Automated Speech Recognition (ASR): An ASR Engine enable bots to process voice-driven interactions and communicate outside of traditional text-based interfaces.

Bot: Bot is a program with artificial intelligence that can simulate a natural conversation with a human. The common synonym is a conversational agent or an intelligent agent.

Deep Learning: Deep Learning is an area of Machine Learning that is based on learning data representations as opposed to task specific algorithms. It is a subfield of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural networks. It is an artificial intelligence function that imitates the workings of the human brain in processing data and creating patterns for use in decision making.
Deployment: The process of publishing a xBot to communication channel (such as Chatra, Facebook Messenger, Olark, Slack, Skype …) where it will be engaged by users.
Dialog Atmosphere: The Dialog Atmosphere feature is a rating system based on natural language processing, text analysis and computational linguistics. The Dialog Atmosphere extract, quantify, and study affective states and subjective information available in conversations.
Disambiguation: Disambiguation refers to the removal of ambiguity by making something clear. Disambiguation requires to determine the meaning of words in a sentence when this word can have several possible meanings. The power of understanding offered by the language Athena© makes it possible to determine the meaning of words in context. This can be set up via a supervised learning method where each distinct intent have a distinct label that can be used in disambiguation question asked by your xBot.

Entity: Entities are the data that can be necessary for a xBot to complete the user’s request. An entity could be a date, a time, a location, a description or any number of things.
Entity extraction: This is the process by which the satisfaction.AI engine identifies words from a user’s sentence and sort them into entities or categories such as for examples names of persons, organizations, locations, expressions of times, quantities, monetary values and percentages.

Intent: The few essential words that describe what the user wants the xBot to do, usually a verb and a noun such as: Find an information, change a password, get a service, etc.
Intent recognition: The process by which satisfaction.AI’s NL engine analyzes the structure of a user’s command to identify each word by meaning, position, conjugation, plurality, and other factors to correctly match the user’s intent to task at hand.
Interface: A shared boundary across which two or more separate components of a computer system exchange information.

Machine Learning: Machine Learning is a type of artificial intelligence (AI) that allows software applications (by using algorithms, patterns, and training data) to become more accurate in predicting outcomes and find hidden insights without being explicitly programmed. It is in other words the capacity of a computer to learn from experience, i.e. to modify its processing on the basis of newly acquired information. This can be done via 2 approaches: the Deep Learning method (please see definition above) and the Reinforcement Learning method (please defnition see below).

Neural network: Artificial neural network is a computer system modeled on the human brain and nervous system. In other words, it is a series of algorithms that attempts to identify underlying relationships in a set of data by using a process that mimics the way the human brain operates. Neural networks have the ability to adapt to changing input so the network produces the best possible result without the need to redesign the output criteria.
NLG: Natural language generation, or NLG, is a subtopic of Natural Language Processing in artificial intelligence, that deals with the generation of natural language from a machine representation system such as a knowledge base or a logical form. With NLG, the system can create a brand new text of a quality similar to a text written by a human being, and thus transform a structured text into a new text understandable by all.
NLP: Natural Language Processing or NLP is the ability of a computer program to understand human speech as it is spoken. It is a process by which a bot or any other system understands and processes requests in common language, rather than programming language.

Natural Language Understanding, or NLU, and Natural Language Generation, or NLG, are sub-disciplines of the NLP.

NLU: Natural language understanding or NLU, is a subtopic of Natural Language Processing in artificial intelligence, that deals with machine reading comprehension. It is the comprehension by computers of the structure and meaning of human language, allowing users to interact with the computer using natural sentences.

Reinforcement Learning: Reinforcement Learning is learning by interacting with an environment. This method allows to learn from the consequences of its actions, rather than from being explicitly taught. The machin selects its actions on basis of its past experiences (exploitation) and also by new choices (exploration), which is essentially trial and error learning. Actions are taken in an environment so as to maximize some notion of cumulative reward.

Sentiment analysis : Sentiment analysis is the capacity to understand a user’s mood throughout a conversation. It is performed on the information exchanged between the user and the xBot. This analysis is based on our Dialog Atmosphere rating system. This rating system is based on natural language processing, text analysis, and computational linguistics which allows us to identify, extract, quantify, and study affective states, and subjective information available in conversations. This analysis is based on our Dialog Atmosphere rating system.
Session : The period of time from when a user engages a xBot, to when they disengage with the xBot.
Structured data : Information with a high degree of organization that is easily searchable when placed in a database.

Unstructured data : Unstructured data and documents, refers to sources that are typically text-heavy and free-flowing. Such documents or data can still contain dates, numbers, and facts, but they lack a pre-defined data model or structure and overall consistency.

X-channel: The process of building one xBot that is “channel agnostic” (meaning the xBot can live in any channel), and cab be deployed to the communication channels of your choice. Your cross channel Bot, can be where your customers are. To interact with your targeted users, you cross channel bot can be integrated with different communication channels, such as your website, traditional chat solutions (such as Olark, Chatra), instant messaging platforms (such as Facebook Messenger, Skype Text) SMS/Text messaging, and VoIP systems. conversations can start in one channel, and continue in another one.

Documented/reviewed 06/11/2017 17:12:55