Prashant Mathur

Learn More
We present a novel online learning approach for statistical machine translation tailored to the computer assisted translation scenario. With the introduction of a simple online feature, we are able to adapt the translation model on the fly to the corrections made by the translators. Additionally, we do online adaption of the feature weights with a large(More)
This paper presents our submissions to the shared translation task at WMT 2011. We created two largely independent systems for English-to-French and Haitian Creole-to-English translation to evaluate different features and components from our ongoing research on these language pairs. Key features of our systems include anaphora resolution, hierarchical(More)
We address a challenging problem frequently faced by MT service providers: creating a domain-specific system based on a purely source-monolingual sample of text from the domain. We solve this problem by introducing methods for domain adaptation requiring no in-domain parallel data. Our approach yields results comparable to state-of-the-art systems optimized(More)
Clustering of insulin resistance and dysmetabolism with obesity is attributed to pathologic adipose tissue. The morphologic hallmarks of this pathology are adipocye hypertrophy and heightened inflammation. However, it's underlying molecular mechanisms remains unknown. Study of gene function in metabolically active tissues like adipose tissue, skeletal(More)
This paper illustrates a way of using para-phrasal interpretation of English nominal compound for translating them into Hindi. Input Nominal compound is first paraphrased automatically with the 8 prepositions as proposed by Lauer (1995) for the task. English prepositions have one-to-one mapping to post-position in Hindi. The English paraphrases are then(More)
We describe effort to improve machine translation of item titles found in a large e-commerce inventory through topic modeling and adaptation. Item titles are short texts which typically contain brand names that do not have to be translated, and item attributes whose translation often depends on the context. Both issues call for robust methods to integrate(More)
In this paper we investigate the problem of adapting a machine translation system to the feedback provided by multiple post-editors. It is well know that translators might have very different post-editing styles and that this variability hinders the application of online learning methods, which indeed assume a homogeneous source of adaptation data. We hence(More)
BACKGROUND Persistent high levels of under-nutrition in India despite economic growth continue to challenge political leadership and policy makers at the highest level. The present inductive enquiry was conducted to map the perceptions of mothers and other key stakeholders, to identify emerging drivers of childhood under-nutrition. METHODS We conducted a(More)
Understanding the role of visceral fat accumulation in the occurrence and progression of metabolic syndrome is of considerable interest. In order to understand the difference between visceral tissue biology of healthy and unhealthy obese individuals, we have used microarray profiling to compare genome-wide expression differences between visceral adipose(More)