Recent methods for learning vector space representations of words have succeeded in capturing fine-grained semantic and syntactic regularities using vector arithmetic, but the origin of these regularities has remained opaque. We analyze and make explicit the model properties needed for such regularities to emerge in word vectors. The result is a new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods. Our model efficiently leverages statistical information by training only on the nonzero elements in a word-word cooccurrence matrix, rather than on the entire sparse matrix or on individual context windows in a large corpus. The model produces a vector space with meaningful substructure, as evidenced by its performance of 75% on a recent word analogy task. It also outperforms related models on similarity tasks and named entity recognition.

/pdf/glove-global-vectors-for-word-representation-55l84hyy3b.pdf

Glove: Global Vectors for Word Representation

Deposits of clastic carbonate-dominated (calciclastic) sedimentary slope systems in the rock record have been identified mostly as linearly-consistent carbonate apron deposits, even though most ancient clastic carbonate slope deposits fit the submarine fan systems better. Calciclastic submarine fans are consequently rarely described and are poorly understood. Subsequently, very little is known especially in mud-dominated calciclastic submarine fan systems. Presented in this study are a sedimentological core and petrographic characterisation of samples from eleven boreholes from the Lower Carboniferous of Bowland Basin (Northwest England) that reveals a >250 m thick calciturbidite complex deposited in a calciclastic submarine fan setting. Seven facies are recognised from core and thin section characterisation and are grouped into three carbonate turbidite sequences. They include: 1) Calciturbidites, comprising mostly of highto low-density, wavy-laminated bioclast-rich facies; 2) low-density densite mudstones which are characterised by planar laminated and unlaminated muddominated facies; and 3) Calcidebrites which are muddy or hyper-concentrated debrisflow deposits occurring as poorly-sorted, chaotic, mud-supported floatstones. These

Phd by thesis

Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models to learn such representations  ignore the morphology of words, by assigning a distinct vector to each word. This is a limitation, especially for languages with large vocabularies and many rare words. In this paper, we propose a new approach based on the skipgram model, where each word is represented as a bag of character n-grams. A vector representation is associated to each character n-gram, words being represented as the sum of these representations. Our method is fast, allowing to train models on large corpora quickly and allows to compute word representations for words that did not appear in the training data. We evaluate our word representations on nine different languages, both on word similarity and analogy tasks. By comparing to recently proposed morphological word representations, we show that our vectors achieve state-of-the-art performance on these tasks.

/pdf/enriching-word-vectors-with-subword-information-22sqq6w40j.pdf

Enriching Word Vectors with Subword Information

Suppose we are given a vector f in a class FsubeRopfN , e.g., a class of digital signals or digital images. How many linear measurements do we need to make about f to be able to recover f to within precision epsi in the Euclidean (lscr2) metric? This paper shows that if the objects of interest are sparse in a fixed basis or compressible, then it is possible to reconstruct f to within very high accuracy from a small number of random measurements by solving a simple linear program. More precisely, suppose that the nth largest entry of the vector |f| (or of its coefficients in a fixed basis) obeys |f|(n)lesRmiddotn-1p/, where R>0 and p>0. Suppose that we take measurements yk=langf# ,Xkrang,k=1,...,K, where the Xk are N-dimensional Gaussian vectors with independent standard normal entries. Then for each f obeying the decay estimate above for some 0<p<1 and with overwhelming probability, our reconstruction ft, defined as the solution to the constraints yk=langf# ,Xkrang with minimal lscr1 norm, obeys parf-f#parlscr2lesCp middotRmiddot(K/logN)-r, r=1/p-1/2. There is a sense in which this result is optimal; it is generally impossible to obtain a higher accuracy from any set of K measurements whatsoever. The methodology extends to various other random measurement ensembles; for example, we show that similar results hold if one observes a few randomly sampled Fourier coefficients of f. In fact, the results are quite general and require only two hypotheses on the measurement ensemble which are detailed

/pdf/near-optimal-signal-recovery-from-random-projections-2mmu9nt75f.pdf

Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?

Suppose we are given a vector $f$ in $\R^N$. How many linear measurements do we need to make about $f$ to be able to recover $f$ to within precision $\epsilon$ in the Euclidean ($\ell_2$) metric? Or more exactly, suppose we are interested in a class ${\cal F}$ of such objects--discrete digital signals, images, etc; how many linear measurements do we need to recover objects from this class to within accuracy $\epsilon$? This paper shows that if the objects of interest are sparse or compressible in the sense that the reordered entries of a signal $f \in {\cal F}$ decay like a power-law (or if the coefficient sequence of $f$ in a fixed basis decays like a power-law), then it is possible to reconstruct $f$ to within very high accuracy from a small number of random measurements.

Near Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?

Keyword-based search engines are in widespread use today as a popular means for Web-based information retrieval Although such systems seem deceptively simple, a considerable amount of skill is required in order to satisfy non-trivial information needs This paper presents a new conceptual paradigm for performing search in context, that largely automates the search process, providing even non-professional users with highly relevant results This paradigm is implemented in practice in the IntelliZap system, where search is initiated from a text query marked by the user in a document she views, and is guided by the text surrounding the marked query in that document (“the context”) The context-driven information retrieval process involves semantic keyword extraction and clustering to automatically generate new, augmented queries The latter are submitted to a host of general and domain-specific search engines Search results are then semantically reranked, using context Experimental results testify that using context to guide search, effectively offers even inexperienced users an advanced search tool on the Web

Placing search in context: the concept revisited.

The Space Complexity of Approximating the Frequency Moments

The frequency moments of a sequence containing mi elements of type i, for 1 i n, are the numbers Fk = P n=1 m k . We consider the space complexity of randomized algorithms that approximate the numbers Fk, when the elements of the sequence are given one by one and cannot be stored. Surprisingly, it turns out that the numbers F0;F1 and F2 can be approximated in logarithmic space, whereas the approximation of Fk for k 6 requires n (1) space. Applications to data bases are mentioned as well.

/pdf/the-space-complexity-of-approximating-the-frequency-moments-u33h2jjrmz.pdf

The space complexity of approximating the frequency moments

Keyword-based search engines are in widespread use today as a popular means for Web-based information retrieval. Although such systems seem deceptively simple, a considerable amount of skill is required in order to satisfy non-trivial information needs. This paper presents a new conceptual paradigm for performing search in context, that largely automates the search process, providing even non-professional users with highly relevant results. This paradigm is implemented in practice in the IntelliZap system, where search is initiated from a text query marked by the user in a document she views, and is guided by the text surrounding the marked query in that document (“the context”). The context-driven information retrieval process involves semantic keyword extraction and clustering to automatically generate new, augmented queries. The latter are submitted to a host of general and domain-specific search engines. Search results are then semantically reranked, using context. Experimental results testify that using context to guide search, effectively offers even inexperienced users an advanced search tool on the Web.

/pdf/placing-search-in-context-the-concept-revisited-34cch7le25.pdf

Placing search in context: the concept revisited

For use with a network having server sites capable of being browsed by users based on identifiers received into the server sites and personal to the users, alternative proxy systems for providing substitute identifiers to the server sites that allow the users to browse the server sites anonymously via the proxy system A central proxy system includes computer-executable routines that process site-specific substitute identifiers constructed from data specific to the users, that transmits the substitute identifiers to the server sites, that retransmits browsing commands received from the users to the server sites, and that removes portions of the browsing commands that would identify the users to the server sites The foregoing functionality is performed consistently by the central proxy system during subsequent visits to a given server site as the same site specific substitute identifiers are reused Consistent use of the site specific substitute identifiers enables the server site to recognize a returning user and, possibly, provide personalized service

Yossi Matias

Papers

Placing search in context: the concept revisited.

The Space Complexity of Approximating the Frequency Moments

The space complexity of approximating the frequency moments

Placing search in context: the concept revisited

System and method for providing anonymous personalized browsing by a proxy system in a network