GAIML: A New Language for Verbal and Graphical Interaction in Chatbots

Abstract

One of the aims of the research in the field of the humancomputer interaction is the design of a natural and intuitive interaction modalities. In particular, many efforts have been devoted in the development of systems able to interact with the user in natural language. Chatbots are the classical interfaces for natural language interaction. Such systems can be very sophisticated, including support for 3D avatars and speech analysis and synthesis. However, all of them present only a text area allowing the user to input her sentences. No doubt, an interaction involving also the natural language can increase the comfort of the userwith respect to common interfaces using only graphical widgets. However, multi-modal communication must be preferred in all those situations when the user and the system have a tight interaction. Typical examples are cultural heritages applications (intelligent museum guides, picture browsing) or systems presenting to the user an information integrated from different sources as in the case of the iGoogle(TM) interface. In this work we present the Graphical Artificial Intelligence Markup Language, an extension of AIML allowing merging of verbal and graphical interaction modalities. A chatbot system, Graphbot, is also presented that is able to support this language. The language is able to define personalized interface patterns that are the most suitable ones in relation to the type of data exchanged between the user and the system during the dialogue.

A critical review of state‐of‐the‐art chatbot designs and applications

“…As people in the modern age become accustomed to visual interactions with digital devices, the provision of a graphical interface has become a promising avenue for future chatbots. Pirrone et al (2008) extended AIML to graphical AIML (GAIML) with verbal and visual interaction modules. Building on GAIML, a conversational system called Graphbot was developed to examine the proposed framework.…”

“…Some existing approaches can be harnessed to realize this goal. For example, the GAIML designed by Pirrone et al (2008) provides a personalized interface, and the Persona‐AIML developed by Galvão et al (2004) enables the use of chatbots with different personalities. However, there remain several unsolved problems, such as the identification of user preference, the optimal strategy for the most appropriate responses, the impact of personality on human–chatbot communications, and the design of specific personalities for users with corresponding preferences.…”

DBOS: A Dialog-Based Object Query System for Hospital Nurses

“…However, if there is an error or ambiguity in word segmentation, synonyms expansion, or word ordering, it becomes difficult to have a rule-based classification system with an appropriate number of rules. R. Pirrone et al [ 11 ] further combined AIML with graphics to dynamically generate a dialog box for users to choose answers from. According to the investigation conducted by Z. Zeng et al [ 12 ], constructing a knowledge base for a professional field requires a huge amount of manual work, even for professionals.…”

Improving Assessment of Students through Semantic Space Construction

“…TutorJ, the system presented in this work, has a natural language module able to interact with users. A further feature in our system is the capability to mix both linguistic and graphical interaction modalities as deeper detailed in a previous work [1].…”