BACKGROUND Ileal intubation is the gold standard for a complete colonoscopy. However, despite evidence of clinical benefit ileoscopy is not always attempted due to perceived technical difficulty. Our aim was to compare time taken for ileal intubation using a new position-the prone 12 o'clock position (PP) with the standard method (left lateral 6 o'clock position-LLP). METHODS We performed a p...

The Microsoft Research translation system is a syntactically informed phrasal SMT system that uses a phrase translation model based on dependency treelets and a global reordering model based on the source dependency tree. These models are combined with several other knowledge sources in a log-linear manner. The weights of the individual components in the loglinear model are set by an automatic ...

Adverse drug reaction (ADR) discovery is the task of identifying unexpected and negative events caused by pharmaceutical products. This paper describes a log-linear Hawkes process model for ADR discovery from longitudinal observational data such as electronic health records (EHRs). The proposed method leverages the irregular time-stamped events in EHRs to represent the time-varying effect of va...

Predictive modelling in the ®eld of dependability, such as repair cost modelling, is usually based on the failure intensity function of repairable systems. The experience feedback data needed to estimate the failure intensity function is, however, seldom available due to the unique character of the systems. Thus approaches that can capture the tacit knowledge of designers, operators and mainten...

We consider the so-called “optimal execution problem” in algorithmic trading, which is the problem faced by an investor who has a large number of stock shares to sell over a given time horizon and whose actions have impact on the stock price. In particular, we develop and study a price model that presents the stochastic dynamics of a geometric Brownian motion and incorporates a log-linear effec...

This paper describes the role of supertagging in a wide-coverage CCG parser which uses a log-linear model to select an analysis. The supertagger reduces the derivation space over which model estimation is performed, reducing the space required for discriminative training. It also dramatically increases the speed of the parser. We show that large increases in speed can be obtained by tightly int...

An M -partition of a positive integer m is a partition with as few parts as possible such that any positive integer less than m has a partition made up of parts taken from that partition of m. This is equivalent to partitioning a weight m so as to be able to weigh any integer weight l < m with as few weights as possible and only one scale pan. We show that the number of parts of an M -partition...

We present three ways of inducing probability distributions on derivation trees produced by Minimalist Grammars, and give their maximum likelihood estimators. We argue that a parameterization based on locally normalized log-linear models balances competing requirements for modeling expressiveness and computational tractability.

We analyse maintenance cost data for Swedish railway infrastructure in relation to traffic volumes and network characteristics, and separate the cost impact from passenger and freight trains. Lines with mixed passenger and freight traffic, and dedicated freight lines are analysed separately using both log-linear and BoxCox regression models. We find that for mixed lines, the Box-Cox specificati...