Task-oriented virtual assistants (or simply chatbots) are in very high demand these days. They employ third-party APIs to serve end-users via natural language interactions. Chatbots are famed for their easy-to-use interface and gentle learning curve (it only requires one of humans' most innate ability, the use of natural language). Studies on human conversation patterns show, however, that day-today dialogues are of multi-turn and multi-intent nature, which pushes the need for chatbots that are more resilient and flexible to this style of conversations. In this paper, we propose the idea of leveraging Conversational State Machine to make it a core part of chatbots' conversation engine by formulating conversations as a sequence of states. Here, each state covers an intent and contains a nested state machine to help manage tasks associated to the conversation intent. Such enhanced conversation engine, together with a novel technique to spot implicit information from dialogues (by exploiting Dialog Acts), allows chatbots to manage tangled conversation situations where most existing chatbot technologies fail.

Task-oriented conversational bots allow users to access services and perform tasks through natural language conversations. However, integrating these bots and software-enabled services has not kept pace with our ability to deploy individual devices and services. The main drawbacks of current bots and services integration techniques stem from the inherent development and maintenance cost. In addition, existing Natural Language Processing (NLP) techniques automate various tasks but the synthesis of API calls to support broad range of potentially complex user intents is still largely a manual and costly process. In this paper, we propose three types of reusable patterns for recognising compositional conversational flows and therefore automatically support increased complexity and expressivity during the conversation.

Attracted by their easy-to-use interfaces and captivating benefits, conversational systems have been widely embraced by many individuals and organizations as side-by-side digital co-workers. They enable the understanding of user needs, expressed in natural language, and on fulfilling such needs by invoking the appropriate backend services (e.g., APIs). Controlling the conversation flow, known as Dialogue Management, is one of the essential tasks in conversational systems and the key to its success and adoption as well. Nevertheless, designing scalable and robust dialogue management techniques to effectively support intelligent conversations remains a deeply challenging problem. This article studies dialogue management from an in-depth design perspective. We discuss the state of the art approaches, identify their recent advances and challenges, and provide an outlook on future research directions. Thus, we contribute to guiding researchers and practitioners in selecting the appropriate dialogue management approach aligned with their objectives, among the variety of approaches proposed so far.