Statistical language learning research takes the view that many traditional natural language processing tasks can be solved by training probabilistic models of language on a sufficient volume of training data. The design of statistical language learners therefore involves answering two questions: (i) Which of the multitude of possible language models will most accurately reflect the properties necessary to a given task? (ii) What will constitute a sufficient volume of training data? Regarding the first question, though a variety of successful models have been discovered, the space of possible designs remains largely unexplored. Regarding the second, exploration of the design space has so far proceeded without an adequate answer. The goal of this thesis is to advance the exploration of the statistical language learning design space. In pursuit of that goal, the thesis makes two main theoretical contributions: it identifies a new class of designs by providing a novel theory of statistical natural language processing, and it presents the foundations for a predictive theory of data requirements to assist in future design explorations. The first of these contributions is called the meaning distributions theory. This theory

A variety of statistical methods for noun compound analysis are implemented and compared. The results support two main conclusions. First, the use of conceptual association not only enables a broad coverage, but also improves the accuracy. Second, an analysis model based on dependency grammar is substantially more accurate than one based on deepest constituents, even though the latter is more preva- lent in the literature.

This article addresses the interpretation of nominalizations, a particular class of compound nouns whose head noun is derived from a verb and whose modifier is interpreted as an argument of this verb. Any attempt to automatically interpret nominalizations needs to take into account: (a) the selectional constraints imposed by the nominalized compound head, (b) the fact that the relation of the modifier and the head noun can be ambiguous, and (c) the fact that these constraints can be easily overridden by contextual or pragmatic factors. The interpretation of nominalizations poses a further challenge for probabilistic approaches since the argument relations between a head and its modifier are not readily available in the corpus. Even an approximation that maps the compound head to its underlying verb provides insufficient evidence. We present an approach that treats the interpretation task as a disambiguation problem and show how we can “re-create” the missing distributional evidence by exploiting partial parsing, smoothing techniques, and contextual information. We combine these distinct information sources using Ripper, a system that learns sets of rules from data, and achieve an accuracy of 86.1 % (over a baseline of 61.5%) on the British National Corpus. 1.

This paper addresses the interpretation of nominalisations, a particular class of compound nouns whose head noun is derived from a verb and whose modifier is interpreted as an argument of this verb. Any attempt to automatically interpret nominalisations needs to take into account: (a) the selectional constraints imposed by the nominalised compound head, (b) the fact that the relation of the modifier and the head noun can be ambiguous, and (c) the fact that these constraints can be easily overridden by contextual or pragmatic factors. The interpretation of nominalisations poses a further challenge for probabilistic approaches since the argument relations between a head and its modifier are not readily available in the corpus. Even an approximation which maps the compound head to its underlying verb provides insufficient evidence. We present an approach which treats the interpretation task as a disambiguation problem and show how we can "recreate" the missing distributional evidence by exploiting partial parsing, smoothing techniques, and contextual information. We combine these distinct information sources using Ripper, a system that learns sets of rules from data, and achieve an accuracy of 86.1% (over a baseline of 61.5%) on the British National Corpus

This paper describes a bootstrapping method for automatically tagging noun compounds with their corresponding semantic relations. Our work takes advantage of the collocation of senses of the noun compound constituents and also word similarity. We exploit this to generate a set of noun compounds from a set of previously tagged noun compounds by replacing one constituent of each noun compound with similar words that are derived from synonyms, hypernyms and sister words. We started with 200 “seed ” noun compounds and generated sets of derived noun compounds with accuracy ranging between 64.72 % and 70.78%. We also evaluated the utility of the automatically derived noun compounds when used in combination with existing noun compound interpretation methods. 1

In this paper we provide benchmark results for two classes of methods used in interpreting noun compounds (NCs): semantic similarity-based methods and their hybrids. We evaluate the methods using 7-way and binary class data from the nominal pair interpretation task of SEMEVAL-2007. 1 We summarize and analyse our results, with the intention of providing a framework for benchmarking future research in this area. 1

Abstract—This paper proposes an unsupervised approach to automatically interpret noun compounds using semantic similarity. Our proposed unsupervised method is based on obtaining a large amount of robust evidence for NC interpretation. In order to obtain evidence sentences for semantic relations (SRs), we first acquired sentences containing both a head noun and its modifier in the form of SR definitions. Then we determined the semantic relations represented in the sentences by looking at the nouns in the test instances (noun mapping) and verbs in the SR definitions (verb mapping). In the noun mapping, we measured the similarity between nouns in test instances and nouns in the collected sentences. In the verb mapping, we mapped the verbs of sentences onto those in the SR definitions. Finally, we built a statistical classifier to interpret noun compounds and evaluated it over 17 SRs defined in [1]. I.