<?xml version="1.0" standalone="yes"?>
<Paper uid="H86-1010">
  <Title>An Equipment Model and Its Role in the Interpretation of Nominal Compounds</Title>
  <Section position="2" start_page="0" end_page="81" type="intro">
    <SectionTitle>
1. Introduction
</SectionTitle>
    <Paragraph position="0"> The work presented here is part of the PROTEUS (-PROtotype TExt Understanding System) system currently under development at the Courant Institute of Mathematical Sciences, New York University. l The objective of our research is to understand short natural language texts about equipment. Our texts at present are CASualty REPorts (CASREPs) which describe failures of equipment installed on Navy ships. Our initial domain is the starting air system for propulsion gas turbines. A typical CASREP consists of several sentences, for example: Unable to maintain lube oil pressure to SAC \[Starting Air Compressor\]. Disengaged immediately after alarm. Metal particles in oil sample and strainer.</Paragraph>
    <Paragraph position="1"> It is widely accepted among researchers that in order to achieve natural language understanding systems robust enough for practical application, it is necessary to provide them with a lot of common-sense and domain-specific knowledge. However, so far, there is no consensus as to what is the best way of choosing, organizing and using such knowledge.</Paragraph>
    <Paragraph position="2"> The novelty of the approach presented here is that, besides general knowledge about equipment, we also use a quite extensive simulation model for the specific piece of equipment which the texts deal with. We found that for understanding purposes it is more appropriate to make the simulation qualitative rather than quantative. Thus, for example, we are not interested in the precise value of oil pressure, but only whether it is too low or too high. The model is built from instances of prototypes which contain the bulk of general knowledge. It exists in the system permanently. In this situation the analysis of a piece of text consists of two stages: (1) locating in the model the objects mentioned in text; (2) interpreting the text using both the specific information residing in the model and the general knowledge which is accessible from the model. There is no clear-cut distinction between these two stages (see discussion of the examples in the next section).</Paragraph>
    <Paragraph position="3"> i An overview of the system is given in \[Grishman 1986\], submitted to the AAAI-86.</Paragraph>
    <Paragraph position="4">  We see the following merits of having a simulation model: (a) the model provides us with a reliable background against which we can check the correctness of the understanding process on several levels: finding referents of noun phrases, assigning semantic cases to verbs, establishing causal relationships between individual sentences of the text.</Paragraph>
    <Paragraph position="5"> (b) the requirements of simulation help us to decide what kind of knowledge about the equipment should be included in the model, how it Could best be organized and which inferences it should be possible to make. It appears that the information needed for simulation largely coincides with that necessary for language understanding.</Paragraph>
    <Paragraph position="6"> (c) the ability to simulate the behavior of a piece of equipment provides a very nice verification method for the understanding process at the level of interaction with a user - it is relatively straightforward to build a dynamic graphical interface which allows the user to have a friendly insight in the way his input has been understoood by the system.</Paragraph>
    <Paragraph position="7"> In the remainder of the paper we will show examples of problems which can be solved only if the system has access to some kind of a simulation model of the domain equipment.</Paragraph>
    <Paragraph position="8"> Having demonstrated the need for such a model, we will discuss the design decisions which we found important for our domain and which seem to apply generally for complex equipment. How these considerations influenced the model for the SAC may be seen in the next section. Then we present a method of finding referents in the model for nominal compounds describing SAC's components. Finally, we briefly describe our future work.</Paragraph>
  </Section>
class="xml-element"></Paper>