<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1417">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Generation of Biomedical Arguments for Lay Readers</Title>
  <Section position="4" start_page="114" end_page="114" type="intro">
    <SectionTitle>
2 System Overview
</SectionTitle>
    <Paragraph position="0"> We are developing a prototype system for genetic counselors that will synthesize the first draft of a patient letter. The deployed system will consist of a graphical user interface for the genetic counselor, a domain model/reasoner, an argument generator, a discourse grammar, and a linguistic realizer. Prototypes of all components except the linguistic realizer have been implemented. Although this paper focuses on discourse generation and its relationship to the domain model, as background we now describe the flow of information through the system.</Paragraph>
    <Paragraph position="1"> The domain model (section 3) is initialized with generic information on clinical genetics. Through a user interface providing menus and other non-freetext input devices, the counselor will provide standard clinical information such as a patient's symptoms and information about his family tree; test results; preliminary diagnosis (before testing); and final diagnosis (after test results are known). The system uses this information to transform its generic domain model into a specialized domain model of the patient and his family.</Paragraph>
    <Paragraph position="2"> In this genre, a patient letter must provide not only the above information, but arguments for the diagnosis and other inferences made by the medical experts. The discourse generation process works as follows. A discourse grammar (section 4) encodes the high-level topic structure of letters in this genre. The discourse grammar rules generate a derivation instantiated from the domain model with information specific to a patient's case. For each of the writer's claims about the case for which a normative argument must be provided according to standard practice, the discourse grammar invokes the argument generator.</Paragraph>
    <Paragraph position="3"> The argument generator (section 5) uses non-domain-specific argument strategies that are instantiated with information from the domain model. The argument generator returns a structured representation of an argument in which the communicative function of information, e.g., as data or warrant, is identified. As illustrated in section 6, in future interactive systems knowledge of communicative function could be used to support follow-up discussion. In the current prototype, this knowledge is used to determine presentation order, e.g., that data supporting a claim is to be presented before that claim. One of the goals of the experiment described in section 7 was to evaluate this ordering. In the final system, the output of discourse generation will be transformed by a linguistic realizer into the first draft of a letter.</Paragraph>
  </Section>
class="xml-element"></Paper>