Supporting Voice-Based Natural Language Interactions for Information Seeking Tasks of Various Complexity
MetadataShow full item record
Natural language interfaces have seen a steady increase in their popularity over the past decade leading to the ubiquity of digital assistants. Such digital assistants include voice activated assistants, such as Amazon's Alexa, as well as text-based chat bots that can substitute for a human assistant in business settings (e.g., call centers, retail / banking websites) and at home. The main advantages of such systems are their ease of use and - in the case of voice-activated systems - hands-free interaction. The majority of tasks undertaken by users of these commercially available voice-based digital assistants are simple in nature, where the responses of the agent are often determined using a rules-based approach. However, such systems have the potential to support users in completing more complex and involved tasks. In this dissertation, I describe experiments investigating user behaviours when interacting with natural language systems and how improvements in design of such systems can benefit the user experience. Currently available commercial systems tend to be designed in a way to mimic superficial characteristics of a human-to-human conversation. However, the interaction with a digital assistant differs significantly from the interaction between two people, partly due to limitations of the underlying technology such as automatic speech recognition and natural language understanding. As computing technology evolves, it may make interactions with digital assistants resemble those between humans. The first part of this thesis explores how users will perceive the systems that are capable of human-level interaction, how users will behave while communicating with such systems, and new opportunities that may be opened by that behaviour. Even in the absence of the technology that allows digital assistants to perform on a human level, the digital assistants that are widely adopted by people around the world are found to be beneficial for a number of use-cases. The second part of this thesis describes user studies aiming at enhancing the functionality of digital assistants using the existing level of technology. In particular, chapter 6 focuses on expanding the amount of information a digital assistant is able to deliver using a voice-only channel, and chapter 7 explores how expanded capabilities of voice-based digital assistants would benefit people with visual impairments. The experiments presented throughout this dissertation produce a set of design guidelines for existing as well as potential future digital assistants. Experiments described in chapters 4, 6, and 7 focus on supporting the task of finding information online, while chapter 5 considers a case of guiding a user through a culinary recipe. The design recommendations provided by this thesis can be generalised in four categories: how naturally a user can communicate their thoughts to the system, how understandable the system's responses are to the user, how flexible the system's parameters are, and how diverse the information delivered by the system is.
Cite this version of the work
Alexandra Vtyurina (2021). Supporting Voice-Based Natural Language Interactions for Information Seeking Tasks of Various Complexity. UWSpace. http://hdl.handle.net/10012/17020