<?xml version="1.0" standalone="yes"?>
<Paper uid="H94-1037">
  <Title>PEGASUS: A Spoken Language Interface for On-Line Air Travel Planning I</Title>
  <Section position="2" start_page="0" end_page="201" type="intro">
    <SectionTitle>
INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Over the past few years, our group has participated, as a member of the ARPA Human Language Technology (HLT) research community, in the development of spoken language technology in the common domain called Air Travel Information Service, or ATIS \[i\]. ATIS permits users to verbally query for air travel information, such as flight schedules from one city to another, obtained from a small relational database excised from the Official Airline Guide. By requiring that all system developers use the same database, it has been possible to compare the performance of various spoken language systems based on their ability to extract the correct information from the database, using a set of prescribed training and test data, and a set of interpretation guidelines. Indeed, periodic common evaluations have occurred at regular intervals, and steady performance improvements have been  does have some shortcomings. First, the current common evaluation focuses on the correctness of the information extracted from the database without any regard to the system's side of the interchange (e.g., clarification queries and helpful suggestions). Thus it has the effect of discouraging research on dialogue-based systems which, we believe, is a crucial aspect of human computer interactions. Second, ATIS makes use of a mock-up, static database containing flight and fare information for a small set of cities within the United States and Canada.</Paragraph>
    <Paragraph position="1"> It is not a realistic model of the databases actually being used by travel agents and travellers. In particular, operational flight information systems are much larger and more complex, and, most impoi'tantly, they contain information which is dynamic in nature.</Paragraph>
    <Paragraph position="2"> The rapid technological progress that we are witnessing gives us hope that spoken language systems capable of performing real tasks will begin to emerge within the decade. To realize this potential, however, it is important that we begin to develop the technology using real databases, so that we can uncover limitations and gaps in our present research paradigm. To this end, we started in 1992 to investigate the feasibility of attaching a spoken language interface to an available on-line database.</Paragraph>
    <Paragraph position="3"> We selected the American Airlines EAASY SABRE system, which allows subscribers to obtain flight information and make flight reservations via a large dynamic database, accessed through their personal computers over the telephone line. This system currently has over 700,000 active subscribers, most of whom are travellers, not travel agents. We selected this database mainly because we believe we can leverage off of our existing ATIS system to build an appropriate user-friendly interface.</Paragraph>
    <Paragraph position="4"> To communicate with EAASY SABRE in its normal mode of operation, users issue coded queries specifying restrictions such as source, date, and fare code. If the necessary pieces of information are omitted from the query, the system enters a tightly controlled menu protocol to fill them in. What we have attempted to accomplish is a replacement of this cumbersome interface with something that permits a more natural dialogue with the computer.</Paragraph>
    <Paragraph position="5"> Our system, called PEGASUS, acts as a mediator between  the user and the EAASY SABRE system, engaging in a spoken dialogue with the user and postprocessing tables delivered by EAASY SABRE for display on the terminal.</Paragraph>
    <Paragraph position="6"> The rest of the paper is organized as follows. We first describe the PEGASUS system, paying particular attention to the conversion of the parse tree to a semantic representation and the multiple roles played by the System Manager, mediating between the user and the EAASY SABRE back-end. We then discuss the dialogue management aspects of the system in some detail. This is followed by some preliminary evaluation results, using data collected from real users planning real trips. Finally, we summarize lessons learned and present our future plans.</Paragraph>
  </Section>
class="xml-element"></Paper>