<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-0743">
  <Title>The Acquisition of Word Order by a Computational Learning System</Title>
  <Section position="7" start_page="217" end_page="217" type="concl">
    <SectionTitle>
4 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> The purpose of this work is to investigate the process of grammatical acquisition from a computational perspective, focusing on the acquisition of word order from data. Five different learners were implemented in this framework and we investigated how the starting point for the learners affects their performance in converging to the target and its interaction with noise. The learners were all converging towards the target grammar, where the different starting points and the presence of noise affected only convergence times, with learners more far away from the target having a slower convergence pattern. Future works include annotating more data to have a bigger corpus, and running more experiments with this corpus, testing how much data is required for all the triggers Noise-Free Environment o4 ,,__., .......</Paragraph>
    <Paragraph position="1"> Learners to converge, with high probability to the target grammar. After that, we will concentrate on investigating the acquisition of subcategorisation frames and argument structure, using the same framework for learning. Although this is primarily a cognitive computational model, it is potentially relevant to the development of more adaptive NLP technology.</Paragraph>
  </Section>
class="xml-element"></Paper>