Unsupervised Language Acquisition: Theory and Practice

TL;DR

This thesis presents novel algorithms for unsupervised learning of syntax and morphology, challenging the argument that humans require innate language knowledge, and demonstrating the feasibility of empiricist language acquisition models.

Contribution

It introduces three new algorithms for unsupervised learning of syntactic categories, morphological processes, and context-free grammars, advancing empirical approaches to language acquisition.

Findings

Algorithms successfully induce syntactic categories from unlabelled text.

Morphological algorithms handle complex languages like Arabic.

Unsupervised grammar induction supports empiricist language models.

Abstract

In this thesis I present various algorithms for the unsupervised machine learning of aspects of natural languages using a variety of statistical models. The scientific object of the work is to examine the validity of the so-called Argument from the Poverty of the Stimulus advanced in favour of the proposition that humans have language-specific innate knowledge. I start by examining an a priori argument based on Gold's theorem, that purports to prove that natural languages cannot be learned, and some formal issues related to the choice of statistical grammars rather than symbolic grammars. I present three novel algorithms for learning various parts of natural languages: first, an algorithm for the induction of syntactic categories from unlabelled text using distributional information, that can deal with ambiguous and rare words; secondly, a set of algorithms for learning morphological processes in a variety of languages, including languages such as Arabic with non-concatenative morphology; thirdly an algorithm for the unsupervised induction of a context-free grammar from tagged text. I carefully examine the interaction between the various components, and show how these algorithms can form the basis for a empiricist model of language acquisition. I therefore conclude that the Argument from the Poverty of the Stimulus is unsupported by the evidence.