*** Welcome to piglix ***

Dialog system


A dialog system or conversational agent (CA) is a computer system intended to converse with a human, with a coherent structure. Dialog systems have employed text, speech, graphics, haptics, gestures and other modes for communication on both the input and output channel.

What does and does not constitute a dialog system may be debatable. The typical GUI wizard does engage in some sort of dialog, but it includes very few of the common dialog system components, and dialog state is trivial.

There are many different architectures for dialog systems. What sets of components are included in a dialog system, and how those components divide up responsibilities differs from system to system. Principal to any dialog system is the dialog manager, which is a component that manages the state of the dialog, and dialog strategy. A typical activity cycle in a dialog system contains the following phases:

Dialog systems that are based on a text-only interface (e.g. text-based chat) contain only stages 2–5.

Dialog systems fall into the following categories, which are listed here along a few dimensions. Many of the categories overlap and the distinctions may not be well established.

"A Natural Dialogue System is a form of dialogue system that tries to improve usability and user satisfaction by imitating human behaviour" (Berg, 2014). It addresses the features of a human-to-human dialog (e.g. sub dialogues and topic changes) and aims to integrate them into dialog systems for human-machine interaction. Often, (spoken) dialog systems require the user to adapt to the system because the system is only able to understand a very limited vocabulary, is not able to react on topic changes, and does not allow the user to influence the dialogue flow. Mixed-initiative is a way to enable the user to have an active part in the dialogue instead of only answering questions. However, the mere existence of mixed-initiative is not sufficient to be classified as natural dialogue system. Other important aspects include:

Although most of these aspects are issues of many different research projects, there is a lack of tools that support the development of dialog systems addressing these topics. Apart from VoiceXML that focusses on interactive voice response systems and is the basis for many spoken dialog systems in industry (customer support applications) and AIML that is famous for the A.L.I.C.E. chatbot, none of these integrate linguistic features like dialog acts or language generation. Therefore, NADIA (a research prototype) gives an idea how to fill that gap and combines some of the aforementioned aspects like natural language generation, adaptive formulation and sub dialogues.


...
Wikipedia

...