Conventional confusion network based system combination for machine translation (MT) heavily relies on features that are based on the measure of agreement of words in different translation hypotheses. This paper presents two new features that consider agreement of n-grams in different hypotheses to improve the performance of system combination. The first one is based on a sentence specific onli...

Several recent papers on Arabic dialect identification have hinted that using a word unigram model is sufficient and effective for the task. However, most previous work was done on a standard fairly homogeneous dataset of dialectal user comments. In this paper, we show that training on the standard dataset does not generalize, because a unigram model may be tuned to topics in the comments and d...

We compute the four-loop contributions to the β-function and the anomalous dimension of the field for the O(N)-invariant N -vector model. These results are used to compute the second analytic corrections to the correlation length and the general spin-n susceptibility.

We present a new edition of the Google Books Ngram Corpus, which describes how often words and phrases were used over a period of five centuries, in eight languages; it reflects 6% of all books ever published. This new edition introduces syntactic annotations: words are tagged with their part-of-speech, and headmodifier relationships are recorded. The annotations are produced automatically with...

Currently, N-gram models are the most common and widely used models for statistical language modeling. In this paper, we investigated an alternative way to build language models, i.e., using artificial neural networks to learn the language model. Our experiment result shows that the neural network can learn a language model that has performance even better than standard statistical methods.

We discuss the large N limit of the supersymmetric CP N models as an illustration of Cecotti and Vafa's tt * formalism. In this limit the 'tt * equation' becomes the long wavelength limit of the 2D Toda lattice, an equation first studied in the context of self-dual gravity. We show how simple finite temperature and large N techniques determine the relevant solution, and verify analytically that...

Estimation of a single-input single-output block-oriented model is studied. The model consists of a linear block embedded between two static nonlinear gains. Hence it is called N-L-N Hammerstein-Wiener model. First the model structure is motivated and the disturbance model is discussed. The paper then concentrates on parameter estimation. A relaxation iteration scheme is proposed by making use ...

We construct a fourth-order derivative CP(N) model in 1 + 1 dimensions by incorporating the topological charge density squared term into the Lagrangian. We quantize the theory by reformulating with auxiliary fields and then performing the path integral explicitly. We discuss the renormalizability in the large N limit and relevance of the effective action with axion physics. PACS Number(s): 11.1...

We determine the phase diagram of the O(n) loop model on the honeycomb lattice, in particular, in the range n>2, by means of a transfer-matrix method. We find that, contrary to the prevailing expectation, there is a line of critical points in the range between n = 2 and infinity. This phase transition, which belongs to the three-state Potts universality class, is unphysical in terms of the O(n)...