We present a semantic and pragmatic account of the anaphoric properties of past and perfect that improves on previous work by integrating discourse structure, aspectual type, surface structure and commonsense knowledge. A novel aspect of our account is that we distinguish between two kinds of temporal intervals in the interpretation of temporal operators-discourse reference intervals and event ...

This work analyzes centered binary Restricted Boltzmann Machines (RBMs) and binary Deep Boltzmann Machines (DBMs), where centering is done by subtracting offset values from visible and hidden variables. We show analytically that (i) centering results in a different but equivalent parameterization for artificial neural networks in general, (ii) the expected performance of centered binary RBMs/DB...

Rocking self-centering (RSC) bridge piers were proposed based on the seismic resilience design theory, pushing development of sustainability. To develop a method for RSC piers, clear understanding their behavior under earthquakes is essential. This study analyzed whole lateral force–displacement response taking into account both rotational and flexural deformation, which resulted in clearer act...

In this paperwe comparepronoun resolution algorithmsand introduce a centering algorithm(LeftRightCentering) that adheres to the constraints and rules of centering theory and is an alternative to Brennan, Friedman, and Pollard’s (1987) algorithm. We then use the Left-Right Centering algorithm to see if two psycholinguistic claims on Cf-list ranking will actually improve pronoun resolution accura...

Centering was formulated as a model of the relationship between attentional state, the form of referring expressions, and the coherence of an utterance within a discourse segment (Grosz, Joshi and Weinstein, 1986; Grosz, Joshi and Weinstein, 1995). In this chapter, I argue that the restriction of centering to operating within a discourse segment should be abandoned in order to integrate centeri...

In this paper, proposes an efficient method for change detection in forest areas using panchromatic stereo imagery and Multispectral imagery using kernel minimum noise fraction analysis. Due to low spectral information it is difficult to extract the change features, since changes mostly occur together with other unrelated changes such as environmental changes and seasonal changes. Hence the ker...