The aim of this paper is to categorize and present the existence of resources for Englishto-Urdu machine translation (MT) and to establish an empirical baseline for this task. By doing so, we hope to set up a common ground for MT research with Urdu to allow for a congruent progress in this field. We build baseline phrase-based MT (PBMT) and hierarchical MT systems and report the results on 3 official independent test sets. On all test sets, hierarchial MT significantly outperformed PBMT. The highest single-reference BLEU score is achieved by the hierarchical system and reaches 21.58% but this figure depends on the randomly selected test set. Our manual evaluation of 175 sentences suggests that in 45% of sentences, the hierarchical MT is ranked better than the PBMT output compared to 21% of sentences where PBMT wins, the rest being equal.

We investigate phrase-based statistical machine translation between English and Urdu, two Indo-European languages that differ significantly in their word-order preferences. Reordering of words and phrases is thus a necessary part of the translation process. While local reordering is modeled nicely by phrase-based systems, long-distance reordering is known to be a hard problem. We perform experiments using the Moses SMT system and discuss reordering models available in Moses. We then present our novel, Urdu-aware, yet generalizable approach based on reordering phrases in syntactic parse tree of the source English sentence. Our technique significantly improves quality of English-Urdu translation with Moses, both in terms of BLEU score and of subjective human judgments.

This paper presents the results of the WMT16 Tuning Shared Task. We provided the participants of this task with a complete machine translation system and asked them to tune its internal parameters (feature weights). The tuned systems were used to translate the test set and the outputs were manually ranked for translation quality. We received 4 submissions in the Czech-English and 8 in the English-Czech translation direction. In addition, we ran 2 baseline setups, tuning the parameters with standard optimizers for BLEU score. In contrast to previous years, the tuned systems in 2016 rely on large data.

Background Tuberous sclerosis complex (TSC) is a rare genetic disorder characterized by benign hamartomas in multiple organs of the body. Renal angiomyolipomas (AML) are commonly associated with TSC. They are mostly asymptomatic. But large and rapidly growing AMLs with the presence of an aneurysm cause symptoms and pose a life-threatening risk for hemorrhage. Case presentation Our patient is a 25-year-old female who presented to us as an undiagnosed case of tuberous sclerosis having a large abdominal mass. She fulfilled the clinical criteria required for the diagnosis of TSC. The CT scan revealed an 18 × 13 × 33 cm fat-containing lesion in the right kidney with an adjacent aneurysm measuring around 16 cm in diameter. Due to the large size of the AML and associated aneurysm, surgical exploration was mandated. On the contralateral kidney, multiple contrast-enhancing soft-tissue densities were present that appeared suspicious on radiology. So a percutaneous biopsy of those lesions was done. Fortunately, it had the same histopathology as an Angiomyolipoma. Nephrectomy of the right-sided kidney with AML has been done. The left-sided lesions that are less than 2 cm and asymptomatic are kept on close surveillance. Any change in size will prompt therapy with mTOR inhibitors. Conclusion When dealing with bilateral renal AML, it is important to adopt a conservative approach. When intervention is indicated, the least invasive strategy should be sought and enacted. Radical surgery should be the last resort.

Background: Patients with life-threatening hemorrhages due to blunt torso trauma are at a particularly high risk of being underdiagnosed. The pulse pressure (PP) starts narrowing down before the traditional parameters start changing, making it a useful tool for assessing and planning early intervention. Objective: To assess the utility of low PP in predicting massive transfusion (MT) or operative intervention in patients with isolated blunt abdominal trauma. Material and methods: A total of 186 patients were included. The PP and mean arterial pressure (MAP) were calculated. Vitals, PP, and MAP were monitored every 15 min during the first 6 h, then every 30 min during the next 6 h, and afterward, every 4 h until discharge. A Chi-square test and an independent t-test (as appropriate) were applied to compare variables with PP at the time of presentation. Differences were considered statistically significant at p-value ≤ 0.05. Results: A total of 55.9% of these patients had injuries due to road traffic accidents (RTA). Emergency operative intervention was provided to 26.3% of the patients. Death was 4.3%. MT was required by 26.3% of the patients. There was a statistically significant association between low PP and sex, length of stay, repeat extended focused assessment with sonography in trauma (eFAST), emergency operational intervention, outcome, MT, number of crystalloids consumed within the first four hours after presentation, injury severity score, systolic blood pressure (SBP), and pulse rate. Conclusion: The PP <30 mmHg was observed as a useful predictor for increased blood loss requiring blood transfusion or operative intervention.