Unsupervised Language Acquisition: Theory and Practice

Unsupervised Language Acquisition: Theory and Practice (2001)

Cached

Download Links

[www.issco.unige.ch]
[www.cs.rhul.ac.uk]

Other Repositories/Bibliography

DBLP

by Alexander Simon Clark

Citations:

32 - 0 self

Versions

Version History

Metadata Version 5

User correction supplied by mph

Datum	Value	Source
TITLE	Unsupervised Language Acquisition: Theory and Practice	user correction - Legacy Corrections
AUTHOR NAME	Alexander Simon Clark	user correction
AUTHOR AFFIL	University of Sussex	user correction
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 nonconcatenative 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.	user correction - Legacy Corrections
YEAR	2001	user correction - Legacy Corrections
CITATIONS	117 found	ParsCit 1.0