Majid Razmara

A novel method for detection of pigment network in dermoscopic images using graphs.

We describe a novel approach to detect and visualize pigment network structures in dermoscopic images, based on the fact that the edges of pigment network structures form cyclic graphs which can be automatically detected and analyzed. First we perform a pre-processing step of image enhancement and edge detection. The resulting binary edge image is converted to a graph and the defined feature patterns are extracted by finding cyclic subgraphs corresponding to skin texture structures. We filtered these cyclic subgraphs to remove other round structures such as globules, dots, and oil bubbles, based on their size and color. Another high-level graph is created from each correctly extracted subgraph, with a node corresponding to a hole in the pigment network. Nodes are connected by edges according to their distances. Finally the image is classified according to the density ratio of the graph. Our results over a set of 500 images from a well known atlas of dermoscopy show an accuracy of 94.3% on classification of the images as pigment network Present or Absent.

Kriya - An end-to-end Hierarchical Phrase-based MT System

Kriya - An end-to-end Hierarchical Phrase-based MT System This paper describes Kriya - a new statistical machine translation (SMT) system that uses hierarchical phrases, which were first introduced in the Hiero machine translation system (Chiang, 2007). Kriya supports both a grammar extraction module for synchronous context-free grammars (SCFGs) and a CKY-based decoder. There are several re-implementations of Hiero in the machine translation community, but Kriya offers the following novel contributions: (a) Grammar extraction in Kriya supports extraction of the full set of Hiero-style SCFG rules but also supports the extraction of several types of compact rule sets which leads to faster decoding for different language pairs without compromising the BLEU scores. Kriya currently supports extraction of compact SCFGs such as grammars with one non-terminal and grammar pruning based on certain rule patterns, and (b) The Kriya decoder offers some unique improvements in the implementation of cube-pruning, such as increasing diversity in the target language n-best output and novel methods for language model (LM) integration. The Kriya decoder can take advantage of parallelization using a networked cluster. Kriya supports both KENLM and SRILM for language model queries. This paper also provides several experimental results which demonstrate that the translation quality of Kriya compares favourably to the Moses (Koehn et al., 2007) phrase-based system in several language pairs while showing a substantial improvement for Chinese-English similar to Chiang (2007). We also quantify the model sizes for phrase-based and Hiero-style systems and also present experiments comparing variants of Hiero models.

Domain adaptation techniques for machine translation and their evaluation in a real-world setting

Statistical Machine Translation (SMT) is currently used in real-time and commercial settings to quickly produce initial translations for a document which can later be edited by a human. The SMT models specialized for one domain often perform poorly when applied to other domains. The typical assumption that both training and testing data are drawn from the same distribution no longer applies. This paper evaluates domain adaptation techniques for SMT systems in the context of end-user feedback in a real world application. We present our experiments using two adaptive techniques, one relying on log-linear models and the other using mixture models. We describe our experimental results on legal and government data, and present the human evaluation effort for post-editing in addition to traditional automated scoring techniques (BLEU scores). The human effort is based primarily on the amount of time and number of edits required by a professional post-editor to improve the quality of machine-generated translations to meet industry standards. The experimental results in this paper show that the domain adaptation techniques can yield a significant increase in BLEU score (up to four points) and a significant reduction in post-editing time of about one second per word.