Irregular and sparse scientific computing programs frequently experience performance losses due to inefficient use of the memory system in most machines. Previous work has shown t...
Michelle Mills Strout, Nissa Osheim, Dave Rostron,...
We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence reordering metrics, and discriminative unigram precision, as well as...
Abstract--Until quite recently, extending Phrase-based Statistical Machine Translation (PBSMT) with syntactic knowledge caused system performance to deteriorate. The most recent su...
Integrating Parts of Speech (POS) information to Machine Translation (MT) model usually amounts to significant changes in the MT decoder. We present a method to rapidly integrate...
: Seriation is an exploratory combinatorial data analysis technique to reorder objects into a sequence along a one-dimensional continuum so that it best reveals regularity and patt...