Over several decades, survival rates of low birth weight (LBW) infants have markedly increased. Following a downward trend from 2007 to 2014, the U.S. low birthweight rate (the percentage of infants born at less than 2,500 grams or 5 lbs., 8 oz.) rose in 2015 to 8.07%, up from 8.00% in 2014. 1 The percentage of very low birthweight (VLBW) infants (less than 1,500 grams) was stable at 1.39% in 2...

In this article, we propose the use of suffix arrays to implement n-gram language models with practically unlimited size n. These unbounded n-grams are called ∞-grams. This approach allows us to use large contexts efficiently to distinguish between different alternative sequences while applying synchronous back-off. From a practical point of view, the approach has been applied within the contex...

Automatic word segmentation errors, for languages having a writing system without word boundaries, negatively affect the performance of language models. As a solution, the use of multiple, instead of unique, segmentation has recently been proposed. This approach boosts N-gram counts and generates new N-grams. However, it also produces bad N-grams that affect the language models' performance. In...