Abstract
Systems that interact in dialogs need to understand linguistic actions being used by one another and know which linguistic actions are appropriate for their own uses. We introduce a model based on conversational action patterns to describe and predict speech acts in natural language dialogs and to specify appropriate actions to satisfy the system's goals. A modified production system was used to implement the formalism. The salient characteristics of the production system are:(1) Affects (emotions) can modify the interpretation of external events and alter the flow of control of the systems.(2) The system uses overlapping and parallel rules to predict and generate overlapping linguistic events in dialog situations.
Recommendations
Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues
CUI '23: Proceedings of the 5th International Conference on Conversational User InterfacesSpoken dialogue systems (SDSs) have been separately developed under two different categories, task-oriented and chit-chat. The former focuses on achieving functional goals and the latter aims at creating engaging social conversations without special ...
Perceived conversational ability of task-based chatbots – Which conversational elements influence the success of text-based dialogues?
AbstractThe use of text-based chatbots offering individual support to customers has increased steadily in recent years. However, thus far, research has focused on comparing text-based chatbots with either each other or with humans, whilst the ...
Highlights- An overview on task-based chatbots and their text-based conversation is given.
- Potential text-based conversation characteristics are identified.
- A usability study and a scenario-based experiment are conducted and analysed.
- The ...
Distilling dialogues: a method using natural dialogue corpora for dialogue systems development
ANLC '00: Proceedings of the sixth conference on Applied natural language processingWe report on a method for utilising corpora collected in natural settings. It is based on distilling (re-writing) natural dialogues to elicit the type of dialogue that would occur if one the dialogue participants was a computer instead of a human. The ...
Comments