<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1118">
  <Title>Controlling Gender Equality with Shallow NLP Techniques</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Times of feminist (language) revolution are gone, but marks are left behind in the form of a changed society with a changed consciousness and changed gender roles. Nevertheless language use seems to oppose changes much stronger than society does. As the use of nondiscriminatory language is nowadays compulsory in administration and o cial documents, a number of guidelines and recommendations exist, which help to avoid gender imbalance and stereotypes in language use. Although in some cases men may be concerned (as for example most terms referring to criminals are masculine nouns) the main concern is about adequate representation of women in language, especially in a professional context. Psychological tests demonstrate that persons reading or hearing masculine job titles (so-called generic terms allegedly meaning both women and men) do not visualize women working in this eld.</Paragraph>
    <Paragraph position="1"> In order to avoid this kind of discrimination two main principles are often suggested (e.g. as in (Ges, 1999; Uni, 2000)):  1. use of gender-neutral language, which rather &amp;quot;disguises&amp;quot; the acting person by using impersonal phrases.</Paragraph>
    <Paragraph position="2"> 2. explicit naming of women and men as equally represented acting persons.</Paragraph>
    <Paragraph position="3">  Using and applying these guidelines in a faithful manner is time-consuming and requires a great amount of practice, which can not always be provided, particularly by unexperienced writer. Moreover these guidelines are often completely unknown in non-feminist circles. A tool which checks texts for discriminatory use of language is thus mandatory to promote written gender equality, educate and remind writer of unacceptable forms to avoid.</Paragraph>
    <Paragraph position="4"> In this paper we describe the project \Gendercheck&amp;quot; which uses a controlled-language authoring tool (CLAT) as a platform and editor to check German texts for discriminatory language. null In section 2 we introduce three categories of gender discrimination in German texts and provide possibilities for their reformulation.</Paragraph>
    <Paragraph position="5"> Section 3 introduces the technology on which the Gendercheck editor is based. The linguistic engine proceeds in two steps, a marking and ltering phase where gender discriminatory formulations are automatically detected. A graphical interface plots the detected formulations and prompts the according messages for correction .</Paragraph>
    <Paragraph position="6"> Section 4 then goes into the detail of the marking and ltering technique. We use the shallow pattern formalism kurd (Carl and Schmidt-Wigger, 1998; Ins, 2004) rst to mark possible erroneous formulations and the to lter out those which occur in \gendered&amp;quot; context. Section 5 evaluates the Gendercheck editor on two texts.</Paragraph>
  </Section>
class="xml-element"></Paper>