This thesis is concerned with the measurement and application of lexical distributional similarity. Two words are said to be distributionally similar if they appear in similar contexts. This loose definition, however, has led to many measures being proposed or adopted from fields such as geometry, statistics, Information Retrieval (IR) and Information Theory. Our aim is to investigate the properties which make a good measure of lexical distributional similarity. We start by introducing the concept of lexical distributional similarity. We discuss potential applications, which can be roughly divided into distributional or language modelling applications and semantic applications, and methods of evaluation (Chapter 2). We look at existing measures of distributional similarity and carry out an empirical comparison of fifteen of these measures, paying particular attention to the effects of word frequency (Chapter 3). We propose a new general framework for distributional similarity based on the context of lexical substitutability, which me measure using the IR concepts of precision and recall. This framework allows us to investigate the key factors in similarity of asymmetry, the relative influence of different contexts and the extent to which words share a context (Chapter 4). Finally, we consider the application of distributional similarity in language modelling (Chapter 5) and as a predictor of semantic similarity using human judgements of similarity and a spelling correction task (Chapter 6).

We propose a range of deep lexical acquisition methods which make use of morphological, syntactic and ontological language resources to model word similarity and bootstrap from a seed lexicon. The different methods are deployed in learning lexical items for a precision grammar, and shown to each have strengths and weaknesses over different word classes. A particular focus of this paper is the relative accessibility of different language resource types, and predicted "bang for the buck" associated with each in deep lexical acquisition applications.

We discuss a range of in vitro and in vivo approaches to deep lexical acquisition, and evaluate a representative sample of each in learning lexical items for a precision grammar. Evaluation focuses particularly on determining the effectiveness of each method at the token and type level, and over the four basic word classes of English. Each method is shown to have particular strengths and weaknesses but to have some part to play in the overall task of word learning. 1

Countability of English nouns is important in various natural language processing tasks. It especially plays an important role in machine translation since it determines the range of possible determiners. This paper proposes a method for reinforcing countability prediction by introducing a novel concept called one countability per discourse. It claims that when a noun appears more than once in a discourse, they will all share the same countability in the discourse. The basic idea of the proposed method is that mispredictions can be correctly overridden using efficiently the one countability per discourse property. Experiments show that the proposed method successfully reinforces countability prediction and outperforms other methods used for comparison. 1

3.1 Mbtg, the tagger generator................................. 4

This paper presents a range of methods for classifying Dutch nouns as countable, uncountable or plural only based on both Dutch and English data. The classification is based on the occurrence of countability specific linguistic features that are extracted from unannotated corpora. We show that in the absence of reliable Dutch gold standard data, cross-linguistic classification can be achieved on the basis of a word-toword or feature-to-feature mapping between English and Dutch.