Qme! : A Speech-based Question-Answering system on Mobile Devices

Access to information has moved on from desktop and laptop computers in office and home environments and is now an any place, any time activity due to mobile devices. Although mobile devices have small keyboards that make typing in text input cumbersome compared to conventional desktop and laptops, the ability to access unlimited amount of information through the Internet using these devices have made them pervasive. Even so, information access using text input on mobile devices with small screens and soft/small keyboards is tedious and unnatural. In addition, by themobile nature of these devices, users often would like to use them in hands-busy environments, ruling out the possibility of typing text. In this paper, we address this issue by allowing the user to query an information repository using speech. We expect that spoken language queries to be a more natural and less cumbersome way of accessing information using mobile devices. A second issue we address is related to directly and precisely answering the user’s query beyond browsing of web pages. This is in contrast to the current approach where a user types in a query using keywords to a search engine, browses the returned results on the small screen to select a potentially relevant document, suitably magnifies the screen to view the document and searches for the answer to her question in the document. By providing a method for the user to pose her query in natural language and presenting the relevant answer(s) to her question, we expect the user’s information need to be fulfilled in a shorter period of time. We present a system, Qme!, for speech-driven question answering as a solution toward addressing these two issues. The system provides a natural input modality – spoken language input for the users to pose their information need and presents a collection of answers that potentially address the information need directly. For a subclass of questions that we term static questions, the system retrieves the answers from an archive of human generated answers to questions. This ensures higher accuracy for the answers retrieved (if found in the archive) and also allows us to retrieve related questions on the user’s topic of interest. For a second subclass of questions that we term dynamic questions, the system retrieves the answer from information databases accessible over the Internet using web forms. The layout of the paper is as follows. In Section 2, we review the related literature. In Section 3, we illustrate the system for speech-driven question answering. We present the retrieval methods we used to implement the system, in Section 4. We evaluate the retrieval methods using text and speech queries and present the results in Section 5.3. We conclude in Section 7.