The Conversational Interface

Abstract

Conversation interfaces (CIs), or chatbots, are a popular form of intelligent agents that engage humans in taskoriented or informal conversation. In this position paper and demonstration, we argue that chatbots working in dynamic environments, like with sensor data, can not only serve as a promising platform to research issues at the intersection of learning, reasoning, representation and execution for goal-directed autonomy; but also handle non-trivial business applications. We explore the underlying issues in the context of Water Advisor, a preliminary multi-modal conversation system that can access and explain water quality data.

Conversational agents in healthcare: a systematic review

“…Based on existing literature, there is a lack of consensus regarding the definitions of conversational agents, dialogue systems, embodied conversational agents, smart conversational interfaces, or chatbots 1 , 8 , 9 , 12 , 13 . Examples of conversational agents include (but are not limited to): chatbots, which have the ability to engage in “small talk” and casual conversation; embodied conversational agents, which involve a computer-generated character (eg avatar, virtual agent) simulating face-to-face conversation with verbal and nonverbal behavior; and smart conversational interfaces such as Apple Siri, Google Now, Microsoft Cortana, or Amazon Alexa 1 , 8 , 9 . For the purposes of this review, we considered the subset of conversational agents that use any unconstrained natural language input.…”

“…The dialogue model takes the preceding context into account with the result that the dialogue evolves dynamically as a sequence of related steps that build on each other. Dialogue initiative (control of the discourse focus) b UserThe user leads the conversationSystemThe system leads the conversationMixedBoth the user and the system can lead the conversation Input modality SpokenThe user uses spoken language to interact with the systemWrittenThe user uses written language to interact with the system Output modality Written, spoken, visual (eg non-verbal communication like facial expressions or body movements) Task-oriented c YesThe system is designed for a particular task and set up to have short conversations, in order to get the necessary information to achieve the goal (eg booking a consultation)NoThe system is not directed to the short-term achievement of a specific end-goal or task (eg purely conversational chatbots)a

Adapted from McTear 2002; 8

b

Adapted from Chu-Carroll et al 1997; 60

c

Adapted from McTear et al. 2016 1

…”

Towards a model for spoken conversational search

“…In recent years, interest in SCS has grown, as speech technology [56] and machine learning for spoken systems [57] have developed. A range of SDS are available, from question answering to semi-conversational systems [28]. Research has been devoted to task-oriented SDS which has defined search boundaries, such as travel planning or route planning, and can be developed with slot filling approaches [55].…”

Motivations, Classification and Model Trial of Conversational Agents for Insurance Companies

“…As a result of the comparison, Dialogflow was chosen as a basic framework. Dialogflow is used for intent identification, which determines the function of a message and based on that a set of possible parameters (McTear et al, 2016). For example, the intent of the message "the display of my smartphone broke" may have the intent phone broken with the parameter damage type as display damage, while the parameter phone type is not given.…”