<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2195">
  <Title>Natural Language Access to Software Applications</Title>
  <Section position="1" start_page="0" end_page="1193" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> This paper reports on the ESPRIT project MELISSA (Methods and Tools for Natural-Language Interfacing with Standard Software Applications) ~. MELISSA aims at developing the technology and tools enabling end users to interface with computer applications, using natural-language (NL), and to obtain a precompetitive product validated in selected end-user applications. This paper gives an overview of the approach to solving (NL) interfacing problem and outlines some of the methods and software components developed in the project.</Paragraph>
    <Paragraph position="1"> Introduction The major goal of MELISSA is to provide the technology and tools enabling software developers to provide a Natural Language (NL) interface for new products, as well as for legacy applications. The project is based on the conviction that NL is the most user friendly interface for specific software applications and for a specific kind of users. NL is 'generic' requiring little or no training. Integrated with speech recognition and speech generation the NL interface is optimally convenient and allows for easy access to software systems by all kinds of (non-expert) users as well as for users with specific disabilities (e.g. visual, motor). MELISSA will deliver three main components: a core of linguistic processing machinery and generic linguistic resources for Spanish, English and German; a set of methods and tools for acquiring and representing the knowledge about the host application and specific linguistic resources required for this application; a set of methods and 1 This project is sponsored by the Commission of the EU under ESPRIT-22252. Project partners are Software AG, Espana, SEMA, France/Spairt, Anite-Systems, Luxembourg, IAI, Germany, ONCE, Spain and the City of Cologne.</Paragraph>
    <Paragraph position="2"> tools for integrating the MELISSA core, the application knowledge, and the host application using the CORBA interoperability standard. The overall architecture of a MELISSA-based NL interface consists of the following software modules: * Speech Recognition Module (SRM), which is a commercial product, providing a continuous speech interface for the other NL modules  or dictates his NL queries to target application The focus of MELISSA is on understanding NL.</Paragraph>
    <Paragraph position="3"> In that, MELISSA addresses problems from knowledge representation and linguistic processing. In the following we concentrate on the design and the interrelation of the linguistic and knowledge-based modules (SRM, LPM, SAM, AKR).</Paragraph>
    <Paragraph position="4"> The MELISSA tools are designed to be generic such that they support development of NL interfaces for a broad range of software applications. This requires an application independent encoding of linguistic resources, and an elaborate modularization scheme supporting flexible configuration of these resources for different software applications.</Paragraph>
    <Paragraph position="5">  Furthermore, successful NL interface must meet with user acceptance requirements regarding response time. This poses a major challenge on the deployment of sophisticated, competence-grammar based NLP technologies as envisaged in MELISSA. One aspect of ensuring efficient performance of a NL interface consists in limiting its capabilities in terms of linguistic coverage. To avoid false (positive or negative) expectations such restrictions must be obviofis to the user. In addition, any restriction in terms of linguistic resources must warrant naturalness of expression.</Paragraph>
  </Section>
class="xml-element"></Paper>