We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decoding, and (c) efficient data formats for translation models and language models. In addition to the SMT decoder, the toolkit also includes a wide variety of tools for training, tuning and applying the system to many translation tasks.

This paper proposes a statistical, treeto-tree model for producing translations. Two main contributions are as follows: (1) a method for the extraction of syntactic structures with alignment information from a parallel corpus of translations, and (2) use of a discriminative, featurebased model for prediction of these targetlanguage syntactic structures-which we call aligned extended projections, or AEPs. An evaluation of the method on translation from German to English shows similar performance to the phrase-based model of Koehn et al. (2003).

Single Image Super Resolution (SISR) is a well-researched problem with broad commercial relevance. However, most of the SISR literature focuses on small-size images under 500px, whereas business needs can mandate the generation of very high resolution images. At Expedia Group, we were tasked with generating images of at least 2000px for display on the website -four times greater than the sizes typically reported in the literature. This requirement poses a challenge that stateof-the-art models, validated on small images, have not been proven to handle. In this paper, we investigate solutions to the problem of generating high-quality images for large-scale 1 super resolution in a commercial setting. We find that training a generative adversarial network (GAN) with attention from scratch using a large-scale lodging image data set generates images with high PSNR and SSIM scores. We describe a novel attentional SISR model for large-scale images, A-SRGAN, that uses a flexible self attention layer to enable processing of large-scale images. We also describe a distributed algorithm which speeds up training by around a factor of five.

We present two methods for incorporating detailed features in a Spanish parser, building on a baseline model that is a lexicalized PCFG. The first method exploits Spanish morphology, and achieves an F1 constituency score of 83.6%. This is an improvement over 81.2% accuracy for the baseline, which makes little or no use of morphological information. The second model uses a reranking approach to add arbitrary global features of parse trees to the morphological model. The reranking model reaches 85.1% F1 accuracy on the Spanish parsing task. The resulting model for Spanish parsing combines an approach that specifically targets morphological information with an approach that makes use of general structural features.