<?xml version="1.0" standalone="yes"?>
<Paper uid="A97-1040">
  <Title>Multilingual Generation and Summarization of Job Adverts: the TREE Project</Title>
  <Section position="9" start_page="274" end_page="275" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> The European Union is a loose geo-political organization that has eleven official languages. As such, it is clear that even in a restricted domain such as that of job ads, novel approaches to Language Engineering are required.</Paragraph>
    <Paragraph position="1"> In this paper we have described an approach that summarizes ads into a base schema, and then generates output in the desired language in a principled, though restricted way. At first glance, this may look like old-fashioned interlingual MT, but there are two important differences. First, our approach is inherently &amp;quot;lossy&amp;quot;, in that not all the information in the input ad may be analysed into the schema. It cannot consequently be included in the generated output.</Paragraph>
    <Paragraph position="2"> Second, the format of the output can be controlled and customised by the user which means again that the output text is a summary or digest, not necessarily presented in the same order as the original text. For both these reasons, our system cannot be descibed as a &amp;quot;translation system&amp;quot;. Nonetheless we believe this approach is capable of giving considerable coverage at a far lower cost and higher quality than that usually associated with MT.</Paragraph>
    <Paragraph position="3"> Our approach is not without some disadvantages however: it is well known that a considerable quantity of the semantics of human language is culturally and socially determined. Thus, even though one can map the names of job categories from one language to another, it is not necessarily true that they mean the same thing. So for example, waiters in Spain are expected to serve snacks, whereas in Belgium they do not. There is of course no easy solution to these  problems from the Language Engineering point of view: our service must simply advise users to check that the job description in the target country corresponds to their understanding.</Paragraph>
    <Paragraph position="4"> Legal constraints are also a significant issue in the area of job advertising. Thus, whilst most countries in the EU have legislation to prevent race and sex discrimination in job advertising, some do not.</Paragraph>
    <Paragraph position="5"> Thus a Spanish bar can (or could until recently) advertise for Pretty girls wanted as bar staff, and Men wanted to work in the kitchen. This type of discrimination is illegal in the UK where it would violate Sex Equality Legislation. Thus we must generate non-discriminatory text to avoid running foul of UK law. This clearly shows how practical applications of Language Engineering have to conform in unforeseen ways to the real world.</Paragraph>
    <Paragraph position="6"> Our future work will continue to extend the pragmatic approach taken so far. In particular, we are being encouraged to broaden the coverage of our system to include many more employment domains. It remains to be seen what are the consequences of this scaling on what has so far proved to be a simple but effective architecture.</Paragraph>
  </Section>
class="xml-element"></Paper>