China
Africa
Explore chapters and articles related to this topic
Communications
Published in David Burden, Maggi Savin-Baden, Virtual Humans, 2019
David Burden, Maggi Savin-Baden
Artificial Intelligence Markup Language (AIML) (Wallace, 2003) is probably the most common pattern matching natural language system. Although it started off as a hobbyist system, it is now used commercially (for example, Pandorabots); it has also been behind many of the finalists and winners in the annual Loebner Prize (an implementation of the Turing Test) (Bradeško and Mladenić, 2012). AIML simply compares the user input, character by character, to a set of patterns in its database, and each pattern is linked to one or more responses that are used if the pattern is the best match for inputted text. The patterns can include wild cards and other features, so a one-for-one match is not needed, but it is still a relatively brute-force approach. Whilst AIML makes no pretence to ‘understand’ what the user is saying, the performance, if well authored, can be very good. However, it does suffer from the need to write more and more cases as the breadth of knowledge increases, making it difficult to scale up.
A Brief History of Artificial Intelligence
Published in Ron Fulbright, Democratization of Expertise, 2020
The Artificial Intelligence Markup Language (AIML) was developed by Richard Wallace from 1995 to 2002 for developing A.L.I.C.E. AIML is an XML-based data structure for representing conversation and dialog primitives. Currently, chatbots using an AIML knowledge base are the most successful in competitions like the Loebner Prize, as shown by the wins by Mitsuku (5 wins), A.L.I.C.E. (3 wins), and Jabberwacky (2 wins) (Bush and Wallace, 2001).
Artificial Intelligence in Cloud Marketing
Published in Frank M. Groom, Stephan S. Jones, Artificial Intelligence and Machine Learning for Business for Non-Engineers, 2019
Lauren Donahue, Fatemeh Hajizadeh
A majority of modern chatbots use AIML, also known as artificial intelligence markup language. AIML is the foundation on which most online chatbots function, due to the fact that they are simple to configure (Satu, 2015).
Applying transfer learning to achieve precision marketing in an omni-channel system – a case study of a sharing kitchen platform
Published in International Journal of Production Research, 2021
Ming-Chuan Chiu, Kai-Hsiang Chuang
Next, in order to fulfil the precision marketing requirement, this study utilised a chatbot based on Artificial Intelligence Markup Language (AIML). AIML derives from Extensible Markup Language (XML), which is used to build up a chatbot artificially. AIML has the ability to characterise data objects and to describe partial programmes that it processes. These data objects consist of two units: topics and categories. Topics are unique to most AIML elements in that they appear outside of category blocks. Categories are basic units of knowledge in AIML. Each category consists of patterns that contain input and templates that inform the reply of the chatbot. In this research, we used patterns to represent the input from users. Additionally, we used templates to inform the responses of the chatbot. With this platform, the service provider could upload information about products with images. Using the CNN model, we were able to obtain more information from the image automatically.
Why Not Robot Teachers: Artificial Intelligence for Addressing Teacher Shortage
Published in Applied Artificial Intelligence, 2018
Bosede I. Edwards, Adrian D. Cheok
The entire system is divided into sections as instructional delivery, pedagogy and learning content, and motion system and sensory (affective) systems. The project employed basic programming languages including java, python, and C+. The conversational part is based on AIML scripts. Parts of the systems that were written in different languages were connected through sockets such that program functions can be called from another language. The development captured factors that relate to the three domains of learning including the cognitive, psychomotor, and affective domains. Hence, the three sections instructional delivery, pedagogy and learning content (cognitive domain), and motion system (psychomotor domain) and sensory system (affective domain).