Search

The research leading to these results has received funding from the European Union's Horizon 2020 research and innovation program under grant agreement no. 823907 (MENHIR project: https://menhir-project.eu) and the Spanish project PID2020-118112RB-C21. Funding for open access charge: Universidad de Granada / CBUA., Conversational interfaces have recently become a ubiquitous element in both the personal sphere by easing access to services, and industrial environments by the automation of services, improved customer support and its corresponding cost savings. However, designing the dialog model used by these interfaces to decide system responses is still a hard-to-accomplish task for complex conversational interactions. This paper describes a data-driven dialog management technique, which provides flexibility to develop, deploy and maintain this module. Various configurations for classification algorithms are assessed with two dialog corpora of different application domains, size, dimensionalities and set of possible system responses. The results of the evaluation show satisfactory accuracy and coherence rates in both tasks. As a proof of concept, our proposal has also been integrated with DialogFlow, a platform provided by Google to design conversational user interfaces. Our proposal has been assessed with a real use case, proving that it can be deployed in conjunction with commercial platforms, obtaining satisfactory results for the objective and subjective assessments completed., CBUA, Universidad de Granada, Horizon 2020- 823907, PID2020-118112RB-C21

Social Virtual Worlds are increasingly being used in education, as their flexibility can be exploited in order to create heterogeneous groups from all over the world who can collaborate synchronously in different virtual spaces. In this paper, the authors describe the potential of virtual worlds as an educative tool to teach and learn abstract concepts by means of programmable 3D objects. They describe the main experiences carried out recently in the application of these technologies in transnational educational activities that combine the Moodle learning resources and programmable 3D objects in the Second Life virtual world.

In service industries such as telecommunications, hotels, insurance, banking, retail, or medical services, companies are increasingly paying more attention to human-computer communication systems that are in direct contact with customers, and focused on achieving the desired profit and market share goals. For this reason, chatbots are increasingly used in service industries starting with simple chat conversation up to more complex functionalities based on soft computing methodologies. Evaluation methodologies for chatbots try to provide an efficient means of assessing the quality of the system and/or predicting the user satisfaction. In this paper we present a clustering approach to provide insight on whether user profiles can be automatically detected from the interaction parameters and overall quality predictions, providing a way of corroborating the most representative features for defining user profiles. We have carried out different experiments for a practical dialog system, from which the clustering approach provided an efficient way of easily distinguishing between different user groups and complete a more significant evaluation of the system.

In this paper we describe a proposal that employs Soft Computing techniques for developing intelligent dialog systems that can improve over time. To do this, our proposal merges statistical dialog management methodologies, intentional and emotional information in order to make dialog managers more efficient and adaptive. The prediction of the user intention and emotion is carried out for each user turn in the dialog by means of specific modules that are conceived as an intermediate phase between natural language understanding and dialog management in the architecture of these systems. We have applied and evaluated our method in the UAH system, for which the evaluation results show that merging both sources of information improves system performance as well as its perceived quality.

Recent advances in Artificial Intelligence, Semantic Web and intelligent interaction devices have made conversational interfaces increasingly popular. These advances in technologies including automatic speech recognition and synthesis, natural language understanding and generation, and dialog management are result of decades of work in these areas to make possible a more natural and intuitive communication with machines. In this chapter, we describe the tremendous potential of Data Science to improve the performance of conversational interfaces and increase the number of users of these interfaces. Following this cycle, the more people use these systems, more data is generated to learn their models and improve their performance, thus increasing the number of users and extending the possibilities for new applications in Digital Business.

Social Virtual Worlds are increasingly being used in education, as their flexibility can be exploited in order to create heterogeneous groups from all over the world who can collaborate synchronously in different virtual spaces. In this paper, the authors describe the potential of virtual worlds as an educative tool to teach and learn abstract concepts by means of programmable 3D objects. They describe the main experiences carried out recently in the application of these technologies in transnational educational activities that combine the Moodle learning resources and programmable 3D objects in the Second Life virtual world.

Designing the rules for the dialog management process is oneof the most resources-consuming tasks when developing a dialog system. Although statistical approaches to dialog management are becoming mainstream in research and industrial contexts, still many systems are being developed following the rule-based or hybrid paradigms. For example, when developers require deterministic system responses to keep total control on the decisions made by the system, or because the infrastructure employed is designed for rule-based systems using technologies currently used in commercial platforms. In this paper, we propose the use of evolutionary algorithms to automatically obtain the dialog rules that are implicit in a dialog corpus. Our proposal makes it possible to exploit the benefits of statistical approaches to build rule-based systems. Our proposal has been evaluated with a practical spoken dialog system, for which we have automatically obtained a set of fuzzy rules to successfully manage the dialog., The research leading to these results has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 823907 (MENHIR project:https://menhir-project.eu)

In this paper we propose to combine speech-based and linguistic classification in order to obtain better emotion recognition results for user spoken utterances. Usually these approaches are considered in isolation and even developed by different communities working on emotion recognition and sentiment analysis. We propose modeling the users emotional state by means of the fusion of the outputs generated with both approaches, taking into account information that is usually neglected in the individual approaches such as the interaction context and errors, and the peculiarities of transcribed spoken utterances. The fusion approach allows to employ different recognizers and can be integrated as an additional module in the architecture of a spoken conversational agent, using the information generated as an additional input for the dialog manager to decide the next system response. We have evaluated our proposal using three emotionally-colored databases and obtained very positive results. Work partially supported by Projects MINECO TEC2012-37832-C02-01, CICYT TEC2011-28626-C02-02, CAM CONTEXTS (S2009/TIC-1485).

Research in techniques to simulate users has a long history within the fields of language processing, speech technologies and conversational interfaces. In this paper, we describe a technique to develop heterogeneous user models that are able to interact with this kind of interfaces. By means of simulated users, it is possible not only to automatically evaluate the overall operation of a conversational interface, but also to assess the impact of the user responses on the decisions that are selected by the system. The selection of the user responses by the simulated user are based on a statistical model that considers the complete history of the interaction to carry out this selection. We describe this technique and its practical application to measure the influence of the most important user's features characteristics that affect the interaction of the simulated user with the a conversational interface.

Technological integration is currently a key factor in teaching and learning. New interaction handheld devices (such as smartphones and tablets) are opening new learning scenarios that require more sophisticated applications and learning strategies. This chapter is focused on the high variety of educational applications that multimodal conversational systems offer. We also describe a framework based on conversational interfaces in mobile learning to enhance the learning process and experience. Our approach focuses on the use of NLP techniques, such as speech and text analytics, to adapt and personalize student’s conversational interfaces . Using this framework, we have developed a practical app that offers different kinds of educative exercises and academic information, which can be easily adapted according to the pedagogical contents and the students’ progress.

Spoken dialog systems have been proposed as a solution to facilitate a more natural human–machine interaction. In this paper, we propose a framework to model the user׳s intention during the dialog and adapt the dialog model dynamically to the user needs and preferences, thus developing more efficient, adapted, and usable spoken dialog systems. Our framework employs statistical models based on neural networks that take into account the history of the dialog up to the current dialog state in order to predict the user׳s intention and the next system response. We describe our proposal and detail its application in the Let׳s Go spoken dialog system. Work partially supported by Projects MINECO TEC2012-37832- C02-01, CICYT TEC2011-28626-C02-02, CAM CONTEXTS (S2009/ TIC-1485)

Smart mobile devices have fostered new interaction scenarios that demand sophisticated interfaces. The main developers of operating systems for such devices provide APIs for developers to implement their own applications, including different solutions for graphical interfaces, sensor control, and voice interaction. Despite the usefulness of such resources, there are no strategies defined for coupling the multimodal interface with the possibilities that the devices offer to identify and adapt to the user needs, which is particularly important in domains such as Ambient Assisted Living. In this paper, we propose a framework that allows developing context-aware multimodal conversational agents that dynamically incorporate user-specific requirements and preferences as well as characteristics about the interaction environment, in order to improve and personalize the service that is provided. Our proposal integrates the facilities of the Android API in a modular architecture that emphasizes interaction management and context-awareness to build user-adapted, robust and maintainable applications. As a proof of concept, we have used the proposed framework to develop an Android app for older adults suffering from Alzheimer's. The app helps them to preserve their cognitive abilities and enhance their relationship with their environment.

With the advances in Language Technologies and Natural Language Processing, conversational interfaces have begun to play an increasingly important role in the design of human-machine interaction systems in a number of devices and intelligent environments. In this paper, we present a statistical model for spoken dialog segmentation and labeling based on a generative model learned using decision trees. We have applied our proposal in a practical conversational system that helps solving simple and routine software and hardware repairing problems. The results of the evaluation show that automatic segmentation of spoken dialogs is very effective for human-machine dialogs. The same statistical model has been applied to human-human conversations and provides a good baseline as well insights in the model limitation.

Smart Mobile Devices Have Fostered New Learning Scenarios That Demand Sophisticated Interfaces. Multimodal Conversational Agents Have Became A Strong Alternative To Develop Human-Machine Interfaces That Provide A More Engaging And Human-Like Relationship Between Students And The System. The Main Developers Of Operating Systems For Such Devices Have Provided Application Programming Interfaces For Developers To Implement Their Own Applications, Including Different Solutions For Developing Graphical Interfaces, Sensor Control And Voice Interaction. Despite The Usefulness Of Such Resources, There Are No Strategies Defined For Coupling The Multimodal Interface With The Possibilities That These Devices Offer To Enhance Mobile Educative Apps With Intelligent Communicative Capabilities And Adaptation To The User Needs. In This Paper, We Present A Practical M-Learning Application That Integrates Features Of Android Application Programming Interfaces On A Modular Architecture That Emphasizes Interaction Management And Context-Awareness To Foster User-Adaptively, Robustness And Maintainability. This work was supported in part by Projects MINECO TEC2012-37832-C02-01, CICYT TEC2011-28626-C02-02, CAM CONTEXTS (S2009/TIC-1485)

The development of multimodal conversational systems is currently a very active research topic. The design and performance of these systems involves different and the interconnection of very heterogeneous components. In this chapter, we describe the rich variety of educative applications of multimodal conversational systems, covering several objectives and strategies that include tutoring, second language learning, learning companions, pedagogical agents, etc. We also describe a general framework to develop pedagogic conversational interfaces for mobile devices. The preliminary evaluation of the application shows the possibilities of our framework to develop pedagogical conversational agents targeted at different populations and pedagogical contents.

Counselling dialogue systems are designed to help users to change and monitor their behaviours in order to achieve beneficial goals, such as the acquisition of healthy habits. To be effective, it is important that these systems include a model that accounts for the effort that users are investing to achieve the goals. However, most of the systems available nowadays carry out a naive calculation based on the attained results, rather than on the reasons behind the successes or failures and their consequences for future user behaviour. In contrast to this, in this paper we propose a model that characterizes user motivation considering various aspects of psychological theories on subjective expected utility and attribution. Moreover, we provide a specification that allows carrying out calculations that replicate the users’ decision-making process considering its emotional implications. The model is general-purpose and can be employed in standard architectures to make interpretations that adapt to each user, thus fostering more flexible and personalized interactions.

This paper describes a toolkit designed to automatically develop dialog managers for spoken dialog system based on evolving Fuzzy-rule-based (FRB) classifiers. The FRB-dialog toolkit allows to develop dialog managers selecting the next system action by considering a set of dynamic rules that are automatically obtained by means of the application of the FRB classification process. Our approach bridges the gap between the academic and industrial perspectives for developing dialog systems, taking into account the data supplied by the user throughout the complete dialog history without causing scalability problems, and also considering confidence measures provided by the recognition and understanding modules.

Conversational interfaces have become a hot topic during the last years. Major research groups and technology companies have been making huge investments in research into technologies such as Artificial Intelligence, deep neural networks, machine learning, and natural language understanding with the aim of creating intelligent assistants that will enable users to interact with information and services in a natural, conversational way. However, most of the current conversational interfaces use hand-crafting dialog strategies and architectures tightly coupled to the application domain and are not adapted to the specific requirements and preferences of each user. In this paper, we propose a multi-agent architecture to develop user-adapted conversational interfaces. Our proposal considers two types of agents. Expert agents access different knowledge sources, and decision agents coordinate them to provide a coherent response to the user. We describe our proposal and its practical application to develop a conversational interface that provides bus schedule information.

HighlightsDialog systems (DS) allow intuitive interaction through natural language.Dialog managers are usually implemented ad hoc and difficult to adapt to new domains.A statistical methodology is proposed to reduce the effort required to develop and adapt dialog managers.User simulation is also proposed to facilitate the acquisition of the required dialog corpus.A complete implementation of our proposal for different dialog systems and its evaluation are also detailed. This paper proposes a domain-independent statistical methodology to develop dialog managers for spoken dialog systems. Our methodology employs a data-driven classification procedure to generate abstract representations of system turns taking into account the previous history of the dialog. A statistical framework is also introduced for the development and evaluation of dialog systems created using the methodology, which is based on a dialog simulation technique. The benefits and flexibility of the proposed methodology have been validated by developing statistical dialog managers for four spoken dialog systems of different complexity, designed for different languages (English, Italian, and Spanish) and application domains (from transactional to problem-solving tasks). The evaluation results show that the proposed methodology allows rapid development of new dialog managers as well as to explore new dialog strategies, which permit developing new enhanced versions of already existing systems.

During recent years, conversational agents have become a solution to provide straightforward and more natural ways of retrieving information in the digital domain. In this article, we present an agent-based dialog simulation technique for learning new dialog strategies and evaluating conversational agents. Using this technique, the effort necessary to acquire data required to train the dialog model and then explore new dialog strategies is considerably reduced. A set of measures has also been defined to evaluate the dialog strategy that is automatically learned and to compare different dialog corpora. We have applied this technique to explore the space of possible dialog strategies and evaluate the dialogs acquired for a conversational agent that collects monitored data from patients suffering from diabetes. The results of the comparison of these measures for an initial corpus and a corpus acquired using the dialog simulation technique show that the conversational agent reduces the time needed to complete the dialogs and improve their quality, thereby allowing the conversational agent to tackle new situations and generate new coherent answers for the situations already present in an initial model. This work was supported in part by Projects MINECO TEC2012-37832-C02-01, CICYT TEC2011-28626-C02-02, CAM CONTEXTS S2009/TIC-1485 Publicado

As conversational technologies develop, we demand more from them. For instance, we want our conversational assistants to be able to solve our queries in multiple domains, to manage information from different usually unstructured sources, to be able to perform a variety of tasks, and understand open conversational language. However, developing the resources necessary to develop systems with such capabilities demands much time and effort, as for each domain, task or language, data must be collected, annotated following an schema that is usually not portable, the models must be trained over the annotated data, and their accuracy must be evaluated. In recent years, there has been a growing interest in investigating alternatives to manual effort that allow exploiting automatically the huge amount of resources available in the web. In this chapter we describe the main initiatives to extract, process and contextualize information from these rich and heterogeneous sources for the various tasks involved in dialog systems, including speech processing, natural language understanding and dialog management.

Speech Technologies and Language Processing have made possible the development of a number of new applications which are based on conversational interfaces. In this paper, we describe two approaches to bridge the gap between the academic and industrial perspectives in order to develop conversational interfaces using an academic paradigm for dialog management while employing the industrial standards. The advances in these technologies have made possible to extend the initial applications of conversational interfaces from only spoken interaction (for instance, by means of VoiceXML-based systems) to multimodal services by means of mobile devices (for instance, using the facilities provided by the Android OS). Our proposal has been evaluated with the successful development of different spoken and multimodal conversational interfaces.

In recent years smart mobile devices have bolstered new interaction scenarios that require more sophisticated human-machine interfaces. The leading developers of operating systems for these devices now provide APIs (Application Programming Interface) for developers to implement their own applications, including different solutions for developing graphical interfaces, control sensors and providing oral interaction. Despite the usefulness of these resources, defined strategies are still needed for developing multimodal interfaces to take greater advantage of these devices for identifying and meeting the needs of users. Currently, these applications are typically ad-hoc and facilitate oral communication only through simple commands. In this paper we propose the practical application of context-sensitive multimodal conversational agents to provide advanced library services that dynamically consider specific user needs and preferences, as well as the specific characteristics of the environment in which the interaction occurs. Such agents would improve and customize the service provided by a mobile device with Internet access. Our proposal integrates features of Android APIs on a modular architecture emphasizing the management of interactions and context awareness in order to create robust applications that can be easily updated and adapted to the user.Los dispositivos móviles inteligentes han fomentado en los últimos años nuevos escenarios de interacción que requieren interfaces persona-máquina más sofisticados. Los principales desarrolladores de sistemas operativos para estos dispositivos proporcionan actualmente APIs (Application Programming Interfaces) para que los desarrolladores puedan implementar sus propias aplicaciones, incluyendo diferentes soluciones para el desarrollo de interfaces gráficas, el control de sensores y proveer interacción oral. A pesar de la utilidad de este tipo de recursos, no se han definido aún estrategias para desarrollar interfaces multimodales que aprovechen las posibilidades que ofrecen estos dispositivos para identificar y adaptarse a las necesidades de los usuarios. De este modo, las aplicaciones suelen desarrollarse ad-hoc y la interfaz oral posibilita únicamente la comunicación mediante comandos simples. En este artículo proponemos la aplicación práctica de agentes conversacionales multimodales sensibles al contexto para proporcionar servicios bibliotecarios avanzados que incorporen dinámicamente necesidades específicas del usuario y sus preferencias, así como las características específicas del entorno en el que se produce interacción, con el fin de mejorar y personalizar el servicio que se proporciona mediante un dispositivo móvil con acceso a Internet. Nuestra propuesta integra funcionalidades de APIs de Android en una arquitectura modular que enfatiza la gestión de la interacción y la sensibilidad al contexto para crear aplicaciones robustas, de fácil actualización y adaptadas al usuario.

The evaluation of conversational interfaces is a continuously evolving research area that encompasses a rich variety of methodologies, techniques, and tools. As conversational interfaces become more complex, their evaluation has become multifaceted. Furthermore, evaluation involves paying attention not only to the different components in isolation, but also to interrelations between the components and the operation of the system as a whole. This chapter discusses the main measures that are employed for evaluating conversational interfaces from a variety of perspectives.

When a user speaks to a conversational interface, the system has to be able to recognize what was said. The automatic speech recognition (ASR) component processes the acoustic signal that represents the spoken utterance and outputs a sequence of word hypotheses, thus transforming the speech into text. The other side of the coin is text-to-speech synthesis (TTS), in which written text is transformed into speech. There has been extensive research in both these areas, and striking improvements have been made over the past decade. In this chapter, we provide an overview of the processes of ASR and TTS.

With the advances in Language Technologies and Natural Language Processing, conversational interfaces have begun to play an increasingly important role in the design of human-machine interaction systems in a number of devices and intelligent environments. One of the most demanding tasks when developing a dialog system consists of selecting the next system response considering the user’s actions and the dialog history, which is the fundamental task related to dialog management. In this paper we present an multiagent-based technique for the development of dialog managers. In our proposal, a multiagent system with specialized dialog agents is designed to deal with each specific subtask of dialog objective for which the dialog system has been designed. The practical application of the proposed technique to develop a dialog system acting as a customer support service shows that the use of these specialized dialog agents increases the quality and number of successful interactions with the system in comparison with developing a single agent to manage the dialog for the complete domain.

We are surrounded by a plethora of smart objects such as devices, wearables, virtual agents, and social robots that should help to make our life easier in many different ways by fulfilling various needs and requirements. A conversational interface is the best way to communicate with this wide range of smart objects. In this chapter, we cover the special requirements of conversational interaction with smart objects, describing the main development platforms, the possibilities offered by different types of device, and the relevant issues that need to be considered in interaction design.

There is a wide range of tools that support various tasks in spoken language, some of which are particularly relevant for processing spoken language understanding in conversational interfaces. Here, the main task is to detect the user’s intent and to extract any further information that is required to understand the utterance. This chapter provides a tutorial on the Api.ai platform that has been widely used to support the development of mobile and wearable devices as well as applications for smart homes and automobiles. The chapter also reviews some similar tools provided by Wit.ai, Amazon Alexa, and Microsoft LUIS, and looks briefly at other tools that have been widely used in natural language processing and that are potentially relevant for conversational interfaces.

There is a wide range of tools that support the generation of rule-based dialog managers for conversational interfaces. However, it is not as easy to find toolkits to develop statistical dialog managers based on reinforcement learning and/or corpus-based techniques. In this chapter, we have selected the VoiceXML standard to put into practice the handcrafted approach, given that this standard is used widely in industry to develop voice user interfaces. The second part of the chapter describes the use of a statistical dialog management technique to show the application of this kind of methodology for the development of practical conversational interfaces.

In this paper we propose combining decision support systems with spoken dialog systems to facilitate training call-center human operators. In our proposal, the system responses are learned automatically from a dialog corpus by means of a statistical approach based on evolving classifiers. This permits inferring knowledge automatically, that is, the system may infer decisions in complex settings where it is not easy to establish clear hand-crafted rules. Also, the training corpus can be provided from human-human recordings so that the experience of highly qualified human operators can be distilled into the system and offered implicitly to the operators being trained with it. Our proposal has been evaluated with a practical spoken dialog system providing railway information, which follows our proposed approach to integrate a decision support system for the selection of the next system action.

The integration of Sentiment Analysis and spoken conversational interfaces provides mutual benefits that enable using context-awareness information to enhance the performance of these interfaces, achieving a more efficient and proactive human-machine communication that can be dynamically adapted to the user's emotional state. In this paper, we describe a novel Sentiment Analysis approach combining a lexicon-based model for specifying the set of emotions and a statistical methodology to identify the most relevant topics in the document that are the targets of the sentiments. Our proposal also includes an heuristic learning method that allows improving the initial knowledge considering the users' feedback. We have integrated the proposed Sentiment Analysis approach into an Android-based mobile App that automatically assigns sentiments to pictures taking into account the description provided by the users.

Conversational interfaces can be built using a variety of technologies. This chapter shows how to create a conversational interface using chatbot technology in which pattern matching is used to interpret the user’s input and templates are used to provide the system’s output. Numerous conversational interfaces have been built in this way, initially to develop systems that could engage in conversation in a human-like way but also more recently to create automated online assistants to complement or even replace human-provided services in call centers. In this chapter, some working examples of conversational interfaces using the Pandorabots platform are presented, along with a tutorial on AIML, a markup language for specifying conversational interactions.

Conversation is a natural and intuitive mode of interaction. As humans, we engage all the time in conversation without having to think about how conversation actually works. In this chapter, we examine the key features of conversational interaction that will inform us as we develop conversational interfaces for a range of smart devices. In particular, we describe how utterances in a conversation can be viewed as actions that are performed in the pursuit of a goal; how conversation is structured; how participants in conversation collaborate to make conversation work; what the language of conversation looks like; and the implications for developers of applications that engage in conversational interaction with humans.

Spoken dialogue systems have been proposed to enable a more natural and intuitive interaction with the environment and human-computer interfaces. In this contribution, we present a framework based on neural networks that allows modeling of the user’s intention during the dialogue and uses this prediction to dynamically adapt the dialogue model of the system taking into consideration the user’s needs and preferences. We have evaluated our proposal to develop a user-adapted spoken dialogue system that facilitates tourist information and services and provide a detailed discussion of the positive influence of our proposal in the success of the interaction, the information and services provided, and the quality perceived by the users.

When they first appeared, conversational systems were developed as speech-only interfaces accessible usually via landline phones. Currently, they are employed in a wide variety of devices such as smartphones and wearables, with different input and output capabilities. Traditional speech-based multimodal interfaces were designed for Web and desktop applications, but current devices pose particular restrictions and challenges for multimodal interaction that must be tackled differently. In this chapter, we discuss these issues and show how they can be solved practically by building several apps for smartwatches using Android Wear that demonstrate the different alternatives available.

With a conversational interface, people can speak to their smartphones and other smart devices in a natural way in order to obtain information, access Web services, issue commands, and engage in general chat. This chapter presents some examples of conversational interfaces and reviews technological advances that have made conversational interfaces possible. Following this, there is an overview of the technologies that make up a conversational interface.

Affect is a key factor in human conversation. It allows us to fully understand each other, be socially competent, and show that we care. As such, in order to build conversational interfaces that display credible and expressive behaviors, we should endow them with the capability to recognize, adapt to, and render emotion. In this chapter, we explain the background to how emotional aspects and personality are conceptualized in artificial systems and outline the benefits of endowing the conversational interface with the ability to recognize and display emotions and personality.

Conversational interfaces have a long history, starting in the 1960s with text-based dialog systems for question answering and chatbots that simulated casual conversation. Speech-based dialog systems began to appear in the late 1980s and spoken dialog technology became a key area of research within the speech and language communities. At the same time commercially deployed spoken dialog systems, known in the industry as voice user interfaces (VUI), began to emerge. Embodied conversational agents (ECA) and social robots were also being developed. These systems combine facial expression, body stance, hand gestures, and speech in order to provide a more human-like and more engaging interaction. In this chapter we review developments in spoken dialog systems, VUI, embodied conversational agents, social robots, and chatbots, and outline findings and achievements from this work that will be important for the next generation of conversational interfaces.