Compounded words are a challenge for NLP applications such as machine translation (MT). We introduce methods to learn splitting rules from monolingual and parallel corpora. We evaluate them against a gold standard and measure their impact on performance of statistical MT systems. Results show accuracy of 99.1% and performance gains for MT of 0.039 BLEU on a German-English noun phrase translation task.
After the domination of behaviourism in Anglo-American psychology during the
middle of the century, the impression has been left, reflected in the many texts on
research design, that the experimental method is the central tool of psychological
research. In fact, a glance through journals will illuminate a wide array of datagathering
instruments in use outside the experimental laboratory and beyond the
While the stochastic volatility (SV) generalization has been shown to
improve the explanatory power over the Black-Scholes model, empirical
implications of SV models on option pricing have not yet been adequately
tested. The purpose of this paper is to ﬁrst estimate a multivariate SV
model using the efﬁcient method of moments (EMM) technique from
observations of underlying state variables and then investigate the respective
effect of stochastic interest rates, systematic volatility and idiosyncratic
volatility on option prices....
This much-needed book, from a selection of top international experts, fills a gap by providing a manual of applied quantitative financial analysis. It focuses on advanced empirical methods for modelling financial markets in the context of practical financial applications.Data, software and techniques specifically aligned to trading and investment will enable the reader to implement and interpret quantitative methodologies covering various models.
This volume contains a refereed selection of papers, which were first presented at the international conference on Numerical Methods for Finance held in Dublin, Ireland in June 2006 and were then submitted for publication. The refereeing procedure was carried out by members of the International Steering Committee, the Local Organizing Committee and the Editors. The aim of the conference was to attract leading researchers, both practitioners and academics, to discuss new and relevant numerical methods for the solution of practical problems in finance.
This book is not a traditional style manual that prescribes mechanical
details such as the forms for levels of headings, typing requirements, and so on. A
number of excellent style manuals, including the Publication Manual of the
American Psychological Association, already cover these matters . Neither will you
find here a discussion of the mechanics of standard English usage; it is assumed
that you have already mastered these. Finally, it is also assumed that you have
already selected an important research topic, applied sound research methods, and
analyzed the data.
This paper proposes to solve the bottleneck of finding training data for word sense disambiguation (WSD) in the domain of web queries, where a complete set of ambiguous word senses are unknown. In this paper, we present a combination of active learning and semi-supervised learning method to treat the case when positive examples, which have an expected word sense in web search result, are only given. The novelty of our approach is to use “pseudo negative examples” with reliable confidence score estimated by a classifier trained with positive and unlabeled examples.
In this paper, we describe an empirical study of Chinese chunking on a corpus, which is extracted from UPENN Chinese Treebank-4 (CTB4). First, we compare the performance of the state-of-the-art machine learning models. Then we propose two approaches in order to improve the performance of Chinese chunking. 1) We propose an approach to resolve the special problems of Chinese chunking. This approach extends the chunk tags for every problem by a tag-extension function. 2) We propose two novel voting methods based on the characteristics of chunking task.
In this paper we present a new approach to controlling the behaviour of a natural language generation system by correlating internal decisions taken during free generation of a wide range of texts with the surface stylistic characteristics of the resulting outputs, and using the correlation to control the generator. This contrasts with the generate-andtest architecture adopted by most previous empirically-based generation approaches, offering a more efficient, generic and holistic method of generator control. ...
This paper presents a status quo of an ongoing research study of collocations – an essential linguistic phenomenon having a wide spectrum of applications in the ﬁeld of natural language processing. The core of the work is an empirical evaluation of a comprehensive list of automatic collocation extraction methods using precision-recall measures and a proposal of a new approach integrating multiple basic methods and statistical classiﬁcation.
We introduce a new method for disambiguating word senses that exploits a nonlinear Kernel Principal Component Analysis (KPCA) technique to achieve accuracy superior to the best published individual models. We present empirical results demonstrating signiﬁcantly better accuracy compared to the state-of-the-art achieved by either na¨ve Bayes ı or maximum entropy models, on Senseval-2 data. We also contrast against another type of kernel method, the support vector machine (SVM) model, and show that our KPCA-based model outperforms the SVM-based model. ...
Thematic knowledge is a basis of semamic interpretation. In this paper, we propose an acquisition method to acquire thematic knowledge by exploiting syntactic clues from training sentences. The syntactic clues, which may be easily collected by most existing syntactic processors, reduce the hypothesis space of the thematic roles. The ambiguities may be further resolved by the evidences either from a trainer or from a large corpus.
A variety of statistical methods for noun compound anMysis 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 prevalent in the literature.
Probabilistic inference is an attractive approach to uncertain reasoning and empirical
learning in artificial intelligence. Computational difficulties arise, however,
because probabilistic models with the necessary realism and
exibility lead to complex
distributions over high-dimensional spaces.
Collection of scientific reports of the best universities honor the author: 10. Nguyen Thi Tuong, Using activities in pairs and in groups to teach writing in English ... English (English English) language is a western branch of the German language group in the Indo-European ), were imported to England through the languages of many peoples conquered in the 6th century.
This paper documents evidence of business cycle synchronization in selected Asia Pacific countries in the 1990s. We explain business cycle synchronization by the channel of international capital flows. Using the VAR method, we find that most Asian countries experience boom-bust cycles following capital inflows, where the boom in output is mostly driven by consumption and investment. Empirical evidence shows that capital flows in the region are highly correlated, which supports the conclusion that capital market liberalization has contributed to business cycle synchronization in Asia.
The concept of polyphony was incorporated by many anthropologists thanks to Mikhail
Bakhtin’s work. Analyzing Dostoevsky’s literature, Bakhtin conclusion was the
following: he was the first to multiply any character; so the relationship between hero
and author was decentralized. Before him, the writing was a monological projection of
the author’s psychology and style on the hero and, consequently, the making peripheral
all the other characters.
OF all disciplines necessary to the criminal justice in addition to
the knowledge of law, the most important are those derived from
psychology. For such sciences teach him to know the type of man
it is his business to deal with. Now psychological sciences appear
in various forms. There is a native psychology, a keenness of vision
given in the march of experience, to a few fortunate persons, who
see rightly without having learned the laws which determine the
course of events, or without being even conscious of them.
Research Reports IWMI’s mission is to improve the management of land and water resources for food, livelihoods and environment. In serving this mission, IWMI concentrates on the integration of policies, technologies and management systems to achieve workable solutions to real problems—practical, relevant results in the field of irrigation and water and land resources.