<?xml version="1.0" standalone="yes"?>
<Paper uid="W01-0720">
  <Title>A Psychologically Plausible and Computationally Effective Approach to Learning Syntax</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Computational learning of natural language can be considered from two common perspectives.</Paragraph>
    <Paragraph position="1"> Firstly, there is the psychological perspective, which leads to the investigation of learning problems similar to those faced by people and the building of systems that seek to model human language learning faculties. Secondly, there is the computational perspective, which seeks to build systems that effectively solve language learning problems that are of practical importance.</Paragraph>
    <Paragraph position="2"> In principle, there is significant overlap between these two perspectives. The most common language learning problems that we wish to solve computationally are frequently those that humans have to solve. For example when humans learn language, especially syntax, it seems to be in a mostly unsupervised setting i.e. there is no annotation of training examples. From a computational perspective, while there are some annotated resources available, in general we have very large amounts of unannotated text available from which we desire to be able to extract grammars, meaning etc. Given this overlap, it seems wise to investigate what we know of the human approach, as humans are good at solving these problems.</Paragraph>
    <Paragraph position="3"> In this work we present a system for learning syntax that seeks to maintain both the psychological and computational perspectives. We also show that this is an effective way to build natural language learning systems. We represent the syntactic knowledge using the Categorial Grammar (CG) formalism, so in Section 2 we introduce CG.</Paragraph>
    <Paragraph position="4"> In Section 3 we aim to define the problem that is to be solved in a way that is psychologically plausible. This is followed in Section 4 by the description of CLL a computational effective solution to the problem, which we maintain is also reasonably psychologically plausible. Related work is discussed in Section 5. The results of experiments using CLL on examples from the Penn Treebank are presented in Section 6 and we draw some conclusions from this work in Section 7.</Paragraph>
  </Section>
class="xml-element"></Paper>