Future Trends for Conversational Agents

Future Trends for Conversational Agents

Diana Pérez-Marín (Universidad Rey Juan Carlos, Spain) and Ismael Pascual-Nieto (Universidad Autónoma de Madrid, Spain)
DOI: 10.4018/978-1-60960-617-6.ch018


In the last decades, there has been a great evolution in the field of Conversational Agents. Currently, there are agents to assist the navigation in Web pages, support elder users when interacting with some computer application to remind them which medicines they should take during the day, or to enhance the learning process by allowing students to review with systems that adapt themselves to their previous knowledge and rhythm of study. In this chapter, the goal is to provide a summary of the future trends that can be envisaged for the future of the field. It is our insight that the future of Conversational Agents are to become pervasive and natural in our daily lives.
Chapter Preview


Fifty years ago, computers were complex machines that occupied rooms and required a vast amount of technical knowledge to be used. Therefore, only a small amount of people could interact with them. Furthermore, users could only communicate with the computers via a very restrictive interface. There was a list of commands with their set of options that should be placed in the exact order in order to command the operation requested to the program.

There has been a great evolution both in the hardware and software aspects of Computer Science since then. While the hardware is being made smaller and more potent, the software is being made friendlier and less dependent on the technical knowledge of the user. Menu-based interfaces have mostly replaced the list of commands. That way, users do not need to memorize the commands. They choose the action to perform by clicking on the menu.

Nevertheless, the interaction based on the use of menus can also be regarded as quite restrictive. All in all, users are limited to request the computer one of the enlisted actions with the options of the panels. Moreover, if the users ignore in which menu an option is, then they will not be able to perform it.

Natural Language Interaction is studied in this book as the possibility of interacting with computers in natural language. That way, users could request the tasks to perform with their computer in the same way than they talk to their colleagues at work. It would not longer necessary to learn lists of commands or where they are placed in a menu.

Conversational agents are programs that interact with the users in natural language. They can be executed in any type of computers (including laptops and netbooks), smartphones or PDAs. These agents are currently being used as assistants to make the navigation in Internet easier, to book travels on-line, remind which medicines to take, do the homework, or attend some customer petitions.

The advantages are many: the agents can work 24 hours per day, all the days of the year, they do not get tired or impatient, and they could be adapted to treat all the people in the same way, or depending on the information previously stored of their profiles, so that they provide exactly what each user needs. In fact, according to Fairclough (2009), the next generation of intelligent technology will be characterized by increased autonomy and adaptive capability.

For the future of Conversational Agents, the advances in Natural Language Processing will keep being crucial. The research into new techniques and algorithms can allow the systems to understand better the sentences provided by the users, and to respond with more elaborated and different constructions as humans would answer to those petitions.

Furthermore, and according to Erwin Van Luhn from Chatbots.org and highlighted in chapters 9 and 17 of this book, the future of conversational agents encompasses more than just the correct understanding and generation of words; it will be about understanding emotions too. Conversational agents could become then part of the users’ everyday life. The agents would be available on demand just by calling out their names as emphatic characters, understanding the users’ lifes, feelings, situation, friendships, history and anticipating like a human would do.

Conversational agents can also have an animated face with or without body. In that case, they are called Embodied Conversational Agents (ECAs). Currently, according to López-Mencía et al. (chapter 3), we are just beginning to understand how ECAs affect the perceptions of users, upon which the most appropriate design of the ECA’s behaviour ultimately depends (Gratch et al., 2006; Edlund & Beskow, 2007). Therefore, it is necessary more research in that line, and it would also be interesting to research the application of ECAs for biometric applications (Krämer et al., 2009).

The chapter is organised as follows: firstly, the future trends on more sophisticated Natural Language Processing, humanising the agents and their pervasiveness are summarised. Next, the chapter is focused on the domain applications and their potential users. Finally, the main conclusions drawn are presented.

Complete Chapter List

Search this Book: