<?xml version="1.0" standalone="yes"?>
<Paper uid="A00-1022">
  <Title>Message Classification in the Call Center</Title>
  <Section position="7" start_page="163" end_page="163" type="concl">
    <SectionTitle>
6 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> We have presented new combinations of STP and SML methods to classify unrestricted e-mail text according to a changing set of categories. The current accuracy of the ICC-MAIL system is 78% (correct solution among the top five proposals), corresponding to an overall performance of 73% since ICC-MAIL processes only 94% of the incoming e-mails. The accuracy improves with usage, since each relearning step will yield better classifiers. The accuracy is expected to approximate that of the agents, but not improve on it. With ICe-MAIL, the performance of an experienced agent can approximately be doubled.</Paragraph>
    <Paragraph position="1"> The system is currently undergoing extensive tests at the call center of AOL Bertelsmann Online. Details about the development of the performance depending on the throughput and change of categories are expected to be available by mid 2000.</Paragraph>
    <Paragraph position="2"> Technically, we expect improvements from the following areas of future work.</Paragraph>
    <Paragraph position="3"> * Further task-specific heuristics aiming at general structural linguistic properties should be defined. This includes heuristics for the identification of multiple requests in a single e-mail that could be based on key words and key phrases as well as on the analysis of the document structure.</Paragraph>
    <Paragraph position="4"> * Our initial experiments with the integration of GermaNet (Hamp and Feldweg, 1997), the evolving German version of WordNet, seem to confirm the positive results described for Word-Net (de Buenaga Rodriguez et al., 1997) and will thus be extended.</Paragraph>
    <Paragraph position="5"> * A reorganization of the existing three-level category system into a semantically consistent tree structure would allow us to explore the non-terminal nodes of the tree for multi-layered SML. This places additional requirements on the knowledge engineering task and thus needs to be thoroughly investigated for pay-off.</Paragraph>
    <Paragraph position="6"> * Where system-generated answers are acceptable to customers, a straightforward extension of ICe-MAIL can provide this functionality. For the application in hand, this was not the case.</Paragraph>
    <Paragraph position="7"> The potential of the technology presented extends beyond call center applications. We intend to explore its use within an information broking assistant in document classification. In a further industrial project with German Telekom, the ICC-MAIL technology will be extended to process multi-lingual press releases. The nature of these documents will allow us to explore the application of more sophisticated language technologies during linguistic preprocessing. null</Paragraph>
  </Section>
class="xml-element"></Paper>