The aim of distributional semantics is to design computational techniques that can automatically learn the meanings of words from a body of text. The twin challenges are: how do we represent meaning, and how do we learn these representations? The current state of the art is to represent meanings as vectors - but vectors do not correspond to any traditional notion of meaning. In particular, there is no way to talk about 'truth', a crucial concept in logic and formal semantics. In this thesis, I develop a framework for distributional semantics which answers this challenge. The meaning of a word is not represented as a vector, but as a 'function', mapping entities (objects in the world) to probabilities of truth (the probability that the word is true of the entity). Such a function can be interpreted both in the machine learning sense of a classifier, and in the formal semantic sense of a truth-conditional function. This simultaneously allows both the use of machine learning techniques to exploit large datasets, and also the use of formal semantic techniques to manipulate the learnt representations. I define a probabilistic graphical model, which incorporates a probabilistic generalisation of model theory (allowing a strong connection with formal semantics), and which generates semantic dependency graphs (allowing it to be trained on a corpus). This graphical model provides a natural way to model logical inference, semantic composition, and context-dependent meanings, where Bayesian inference plays a crucial role. I demonstrate the feasibility of this approach by training a model on WikiWoods, a parsed version of the English Wikipedia, and evaluating it on three tasks. The results indicate that the model can learn information not captured by vector space models.

Automatic syntactic analysis is essential for extracting useful information from large-scale learner data for linguistic research and natural language processing (NLP). Currently, researchers use standard POS taggers and parsers developed on native language to analyze learner language. Investigation of how such systems perform on learner data is needed to develop strategies for minimizing the cross-domain effects. Furthermore, POS taggers and parsers are developed for generic NLP purposes and may not be useful for identifying specific syntactic constructs such as subcategorization frames (SCFs). SCFs have attracted much research attention as they provide unique insight into the interplay between lexical and structural information. An automatic SCF identification system adapted for learner language is needed to facilitate research on L2 SCFs. In this thesis, we first provide a comprehensive evaluation of standard POS taggers and parsers on learner and native English. We show that the common practice of constructing a gold standard by manually correcting the output of a system can introduce bias to the evaluation, and we suggest a method to control for the bias. We also quantitatively evaluate the impact of fine-grained learner errors on POS tagging and parsing, identifying the most influential learner errors. Furthermore, we show that the performance of probabilistic POS taggers and parsers on native English can predict their performance on learner English. Secondly, we develop an SCF identification system for learner English. We train a machine learning model on both native and learner English data. The system can label individual verb occurrences in learner data for a set of 49 distinct SCFs. Our evaluation shows that the system reaches an accuracy of 84\% F1 score. We then demonstrate that the level of accuracy is adequate for linguistic research. We design the first multidimensional SCF diversity metrics and investigate how SCF diversity changes with L2 proficiency on a large learner corpus. Our results show that as L2 proficiency develops, learners tend to use more diverse SCF types with greater taxonomic distance; more advanced learners also use different SCF types more evenly and locate the verb tokens of the same SCF type further away from each other. Furthermore, we demonstrate that the proposed SCF diversity metrics contribute a unique perspective to the prediction of L2 proficiency beyond existing syntactic complexity metrics.

Thesis (DAppLing)--Macquarie University, Division of Linguistics and Psychology, Dept. of Linguistics, 2009. / "September 2008". Bibliography: p. 189-196.

Thesis (M.A.)--University of Hong Kong, 1989. / Also available in print.

The thesis examines the issue of gender in textbooks. The aim of the thesis is to analyse three sets of Czech language secondary school textbooks and ascertain, whether these textbooks contribute to the propagation of gender stereotypes in the society or whether they do not. The thesis is divided into a theoretical section and an empirical section. The theoretical section firstly explicates the fundamental concepts of gender, secondly focuses on the discrimination of women via language and on other topics from the field of gender linguistics. The last chapter of the theoretical section focuses on how gender stereotypes influence schooling. The empirical section encompasses the aforementioned analysis of the selected Czech language textbook sets. The analysis further investigates the manner in which men and women are represented in the curriculum, how men and women are portrayed in the illustrations, if the linguistic means are gender-balanced, and also whether the textbooks include any gender linguistics topics. The results of the analysis show that in all textbook sets, men are the dominant gender in illustrations, as well as among significant figures and authors of literary excerpts. In terms of roles, employment and character traits that are attached to individual characters, the sets of...

Vom 18. bis 20. September 2014 kam die Gruppe der JungslavistInnen zu ihrem 23. Treffen in Dresden zusammen. Die Tagung, die am Institut für Slavistik an der TU Dresden stattfand, beinhaltete ein breites Spektrum an Beiträgen aus der synchronen und diachronen Linguistik, Semantik und Pragmatik, Kontaktlinguistik und Kleinsprachenforschung. Präsentiert wurden außerdem Arbeitsergebnisse aus den Bereichen der Schriftlinguistik, genderorientierten Sprachwissenschaft sowie kulturwissenschaftlichen Linguistik. Die ausgewählten Aspekte und Problematiken der linguistischen Forschung wurden an zahlreichen Beispielen aus der Ost-, West- und Südslavia illustriert.

Since recent years, the use of non-traditional data sources by hedge funds in order to support investment decisions has increased. One of the data sources which has increased most is social media and it has become popular to analyze the public opinion with help of sentiment analysis in order to predict the performance of a company. In order to evaluate the public opinion one need big sets of Twitter data. The Twitter data was collected by streaming the Twitter feed and the stock data was collected from a Bloomberg Terminal. The aim of this study was to examine if there is a correlation between the public opinion of a stock and the stock price, and also what affects this relationship. While such a relationship cannot be established in general, we are able to show that if the data quality is good, there is a high correlation between the public opinion and stock price, and that significant events surrounding the company results in a higher correlation during that period. / De senaste åren har användandet av icke-traditionella datakällor ökat av hedgefonder för att ta investeringsbeslut. En av datakällorna som blivit populära är sociala medier och det har blivit vanligt att analysera folkopinionen med hjälp av sentimentanalys för att kunna förutspå ett företags resultat. För att analysera folkopinionen krävdes stora mängder Twitterdata. Twitter-datan hämtades genom att strömma Twitter-flödet och aktiedatan hämtades från en Bloomberg Terminal. Målet med studien var att undersöka ifall det finns en korrelation mellan folkopinionen av en aktie och aktiens prisutveckling, och även vad som påverkar denna relationen. Även om en sådan relation inte kan fastställas i allmänhet så kan vi visa att om datakvaliten är god, så finns det en hög korrelation mellan folkopinionen och aktiepriset, samt att vid betydande händelser som rör företaget, så resultar det i en hög korrelation under den perioden.

The provision of compositionality in distributional models of meaning, where a word is represented as a vector of co-occurrence counts with every other word in the vocabulary, offers a solution to the fact that no text corpus, regardless of its size, is capable of providing reliable co-occurrence statistics for anything but very short text constituents. The purpose of a compositional distributional model is to provide a function that composes the vectors for the words within a sentence, in order to create a vectorial representation that re ects its meaning. Using the abstract mathematical framework of category theory, Coecke, Sadrzadeh and Clark showed that this function can directly depend on the grammatical structure of the sentence, providing an elegant mathematical counterpart of the formal semantics view. The framework is general and compositional but stays abstract to a large extent. This thesis contributes to ongoing research related to the above categorical model in three ways: Firstly, I propose a concrete instantiation of the abstract framework based on Frobenius algebras (joint work with Sadrzadeh). The theory improves shortcomings of previous proposals, extends the coverage of the language, and is supported by experimental work that improves existing results. The proposed framework describes a new class of compositional models thatfind intuitive interpretations for a number of linguistic phenomena. Secondly, I propose and evaluate in practice a new compositional methodology which explicitly deals with the different levels of lexical ambiguity (joint work with Pulman). A concrete algorithm is presented, based on the separation of vector disambiguation from composition in an explicit prior step. Extensive experimental work shows that the proposed methodology indeed results in more accurate composite representations for the framework of Coecke et al. in particular and every other class of compositional models in general. As a last contribution, I formalize the explicit treatment of lexical ambiguity in the context of the categorical framework by resorting to categorical quantum mechanics (joint work with Coecke). In the proposed extension, the concept of a distributional vector is replaced with that of a density matrix, which compactly represents a probability distribution over the potential different meanings of the specific word. Composition takes the form of quantum measurements, leading to interesting analogies between quantum physics and linguistics.

Doct. thesis Univ. of Manchester, 2005. / Includes bibliographical references and index.

This master thesis deals with the construction of a system for automatic classification of~unknown words based on derivation bonds. For this purpose, the system was designed to~extract derivative links based on electronic dictionaries and to create word-forming models from them. Based on this knowledge, it is then possible to incorporate unclassified words into existing nests formed from the obtained bonds, and their models, or create new ones. The reader will be gradually acquainted with the reasons that lead to the continuous transformation or expansion of the lexicon, the ways in which the words in~the~Czech language are derived and how to obtain information about the changes caused by this derivation process. This system builds on and extends the research of the branch of morphology in~the~project of a morphological analyzer of the Research Group of Knowledge Technologies, working at the Faculty of Information Technology of the Brno University of~Technology.