<?xml version="1.0" standalone="yes"?>
<Paper uid="A00-2017">
  <Title>A Classification Approach to Word Prediction*</Title>
  <Section position="6" start_page="129" end_page="130" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper presents a new approach to word prediction tasks. For each word of interest, a word representation is learned as a function of a common, but 4In this experiment, the vowels phonemes were divided into two different groups to account for different sounds.</Paragraph>
    <Paragraph position="1">  potentially very large set of expressive (relational) features. Given a prediction task (a sentence with a missing word) the word representations are evaluated on it and compete for the most likely word to complete the sentence.</Paragraph>
    <Paragraph position="2"> We have described a language that allows one to define expressive feature types and have exhibited experimentally the advantage of using those on word prediction task. We have argued that the success of this approach hinges on the combination of using a large set of expressive features along with a learning approach that can tolerate it and converges quickly despite the large dimensionality of the data. We believe that this approach would be useful for other disambiguation tasks in NLP.</Paragraph>
    <Paragraph position="3"> We have also presented a preliminary study of a reduction in the confusion set size and its effects on the prediction performance. In future work we intend to study ways that determine the appropriate confusion set in a way to makes use of the current task properties.</Paragraph>
  </Section>
class="xml-element"></Paper>