<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0504">
  <Title>Legend: Language Swedish Swedish</Title>
  <Section position="6" start_page="26" end_page="27" type="concl">
    <SectionTitle>
6 Testing the New Version of Profet&amp;quot;
</SectionTitle>
    <Paragraph position="0"> Preliminary quantitative tests of the new prediction system were run with an evaluation program developed at the laboratory. This was done without vs with an increasing number of grammatical tag types: (1) unigrams, (2)unigrams and bigrams, and (3) unigrams, bigrams, and trigrams. The test texts consisted of two types: a 10,000-word section of a novel of which the rest was used in the development of the lexicon of the predictor, and a 7500-word collection of essays written by students at the Stockholm Institute of Education and not used in the lexicon development. Each of the text types was divided into a 1000-word section and a 5000- word section, each of which was contained within the larger. The  test results seem to indicate that the most significant keystroke savings are furnished by the grammatical bigrams: at least 7.4% over the grammatical unigrams, whose minimum savings amount to a mere 3.1% compared to prediction without any grammatical information. The most substantial savings are scored by the grammatical bigrams in the four largest texts: 27.3% - 33.6% in the essay texts (non-lexicon-corpus) and 16% in each of the novel texts (lexicon corpus). Unexpectedly, grammatical trigrams do not appear to add more than 1% in savings, at the most, over bigrams. However, further testing is needed. They are expected to at least be of a qualitative value to the user.</Paragraph>
    <Paragraph position="1"> In our present study, the aim of which is the comparison between the current and new versions of Profet, a test design similar to the one described in the two evaluation studies above will be used. A base-line based on their current method of writing will be established prior to the introduction of the new Prolet version. Test tasks will include dictation and free writing. The subjects must be linguistically competent enough to benefit from the different features of the new version of Profet, i.e., able to make a choice.</Paragraph>
    <Paragraph position="2"> When the inflections of a specific word are presented visually or aurally, the subject must be able to distinguish between the forms and make the correct selection. Two subjects with motoric dysfunction and reading and writing difficulties and five persons with dyslexia will participate in the evaluation of the new version. The two subjects with motoric dysfunction have participated in the earlier studies and are well acquainted with computers and writing support. A baseline based on the current version of Profet has already been established. Our goal, then, is to compare texts written by these two individuals with the current vs new version, respectively, of Profet. The five subjects with dyslexia have reading and writing difficulties as their main problem. Therefore, speed and efficiency will not be studied. Tentative results from the Profet evaluation will be presented at the * workshop in Madrid in July 1997.</Paragraph>
  </Section>
class="xml-element"></Paper>