It is common for conclusions of empirical studies to depend on multiple significant outcomes. This practice may seem reasonable, but it has some unintended effects. In particular, the compound Type I error rate (the likelihood concluding that an effect exists when does not) can be much lower than individual studies. in itself not a problem since low desirable. However, there also accompanying d...

Document retrieval in languages with a rich and complex morphology – particularly in terms of derivation and (single-word) composition – suffers from serious performance degradation with the stemming-only query-term-totext-word matching paradigm. We propose an alternative approach in which morphologically complex word forms are segmented into relevant subwords (such as stems, prefixes, suffixes...

We describe the neural machine translation system submitted by the University of Rochester to the Chinese-English language pair for the WMT 2017 news translation task. We applied unsupervised word and subword segmentation techniques and deep learning in order to address (i) the word segmentation problem caused by the lack of delimiters between words and phrases in Chinese and (ii) the morpholog...

This paper gives an overview of the multimedia instructions that have been added to the instruction set architectures of general-purpose microprocessors to accelerate media processing. Examples are MAX, MMX and VIS, the multimedia extensions for PA-RISC, ix86, and SPARC processor architectures. We describe subword parallelism, a low overhead form of SIMD parallelism, and the classes of instruct...

Word posterior probability (WPP) computed over LVCSR word graphs has been used successfully in measuring confidence of speech recognition output. However, for certain applications the word graph is too sparse to warrant reliable WPP estimation. In this paper, we incorporate subword units as background models to generate a subword graph for estimating posterior probability. Experiments on both E...

Mix-automatic sequences form a proper extension of the class of automatic sequences, and arise from a generalization of finite state automata where the input alphabet is state-dependent. In this paper we compare the class of mix-automatic sequences with the class of morphic sequences. For every polynomial φ we construct a mix-automatic sequence whose subword complexity exceeds φ. This stands in...