<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-2043">
  <Title>Illuminating Trouble Tickets with Sublanguage Theory</Title>
  <Section position="5" start_page="171" end_page="171" type="concl">
    <SectionTitle>
5 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> Initial exploration of the Trouble Tickets revealed their strong sublanguage characteristics, such as: wide use of domain-specific terminology, abbreviations and phrases; odd grammar rules favoring shorthand; and special discourse structure reflective of the communicative purpose of the tickets.</Paragraph>
    <Paragraph position="1"> The identified linguistic patterns are sufficiently consistent across the data, so that they can be described algorithmically to support effective automated identification of ticket sections and semantic components.</Paragraph>
    <Paragraph position="2"> Experimentation with classification algorithms shows that applying the sublanguage theoretical framework to the task of mining trouble ticket data appears to be a promising approach to the problem of reducing human error and, thus, expanding the scope of data amenable to data mining techniques that use Trouble Type information.</Paragraph>
    <Paragraph position="3"> Our directions for future research include experimenting with other machine learning techniques, utilizing the newly-gained knowledge of the tickets' sublanguage grammar, as well as testing sublanguage analysis technology on other types of field service reports.</Paragraph>
  </Section>
class="xml-element"></Paper>