, and it is a problem that one always encounters while collecting fre-quency statistics on words and word sequences (m-grams) from a text of finite size. This means that even for a very large data col-lection, the maximum likelihood estimation method does not allow Turing’s estimate PT for a probability of a

We introduce an Icelandic corpus of more than 250 million running words and de-scribe the methodology to build it. The re-source is available for use free of charge. We provide automatically generated mono-lingual lexicon entries, comprising fre-quency statistics, samples of usage, co

one performs best. All methods considered in this paper are based on word and ngram fre-quencies; the strategy is defended. 1

We present a simple and efficient approach for deriving bilingual dic-tionaries from sentence-aligned par-allel text by extending the notion of co-occurrences to a cross-lingual setting. Dictionaries are evaluated against gold standards and manu-ally; the analysis accounts for fre-quency and corpus

-erties of the native language. A simple attractor model suffices to account for these and previous results on loss of discrimination of non-native-language contrasts and suggests that the technique of measuring graded loss of multiple contrasts, in combination with observation of input fre-quencies, can offer a

We investigate invariant random fields on the sphere using a new type of spherical wavelets, called needlets. These are compactly supported in fre-quency and enjoy excellent localization properties in real space, with quasi-exponentially decaying tails. We show that, for random fields on the sphere

of the low spatial fre-quency (SF) structure of the image. We develop a simple computational model that relies on the statistics of natural scenes actively to reconstruct the image that is most likely to have caused an observed series of responses across SF channels. This principle is tested psychophysically

. As Buck (1985) recently suggested, most studies indicate that, compared to men, women express greater mathemat-ics anxiety and perform less well in mathematics and mathematics-related courses. Comparing letter grade fre-quencies for men and women in her statistics classes, she found "no significant

frequencies of linear sto-chastic systems is derived. The proposed method does not employ the small-randomness andGaussian random variable assumption usually used in the perturbation based methods. Joint distributions of the natural fre-quencies are investigated using numerical examples and the results

this line of research is the power of representation formats. For instance, information presented by means of natural fre-quencies, numerical or pictorial, fosters the understanding of statistical information and improves probabilistic reasoning, whereas conditional probabilities tend to im