Dramatic improvements in DNA sequencing technology have revolutionized our ability to characterize most genomic diversity. However, accurate resolution of large structural events has remained challenging due to the comparatively shorter read lengths of second-generation technologies. Emerging third-generation sequencing technologies, which yield markedly increased read length on rapid time scales and for low cost, have the potential to address assembly limitations. Here we combine sequencing data from second- and third-generation DNA sequencing technologies to assemble the two-chromosome genome of a recent Haitian cholera outbreak strain into two nearly finished contigs at > 99.9% accuracy. Complex regions with clinically significant structure were completely resolved. In separate control assemblies on experimental and simulated data for the canonical N16961 reference we obtain 14 and 8 scaffolds greater than 1kb, respectively, correcting several errors in the underlying source data. This work provides a blueprint for the next generation of rapid microbial identification and full-genome assembly.

We propose a methodology for building a practical robust query classification system that can identify thousands of query classes with reasonable accuracy, while dealing in realtime with the query volume of a commercial web search engine. We use a blind feedback technique: given a query, we determine its topic by classifying the web search results retrieved by the query. Motivated by the needs of search advertising, we primarily focus on rare queries, which are the hardest from the point of view of machine learning, yet in aggregation account for a considerable fraction of search engine traffic. Empirical evaluation confirms that our methodology yields a considerably higher classification accuracy than previously reported. We believe that the proposed methodology will lead to better matching of online ads to rare queries and overall to a better user experience.

Keyword 3 generation for search engine advertising is an important problem for sponsored search or paidplacement advertising. A recent strategy in this area is bidding on nonobvious yet relevant words, which are economically more viable. Targeting many such nonobvious words lowers the advertising cost, while delivering the same click volume as expensive words. Generating the right nonobvious yet relevant keywords is a challenging task. The challenge lies in not only finding relevant words, but also in finding many such words. In this paper, we present TermsNet, a novel approach to this problem. This approach leverages search engines to determine relevance between terms and captures their semantic relationships as a directed graph. By observing the neighbors of a term in such a graph, we generate the common as well as the nonobvious keywords related to a term.

Understanding a medical conversation between a patient and a physician poses unique natural language understanding challenge since it combines elements of standard open-ended conversation with very domainspecific elements that require expertise and medical knowledge. Summarization of medical conversations is a particularly important aspect of medical conversation understanding since it addresses a very real need in medical practice: capturing the most important aspects of a medical encounter so that they can be used for medical decision making and subsequent follow ups.In this paper we present a novel approach to medical conversation summarization that leverages the unique and independent local structures created when gathering a patient's medical history. Our approach is a variation of the pointer generator network where we introduce a penalty on the generator distribution, and we explicitly model negations. The model also captures important properties of medical conversations such as medical knowledge coming from standardized medical ontologies better than when those concepts are introduced explicitly. Through evaluation by doctors, we show that our approach is preferred on twice the number of summaries to the baseline pointer generator model and captures most or all of the information in 80% of the conversations making it a realistic alternative to costly manual summarization by medical experts.

We propose a methodology for building a robust query classification system that can identify thousands of query classes, while dealing in real time with the query volume of a commercial Web search engine. We use a pseudo relevance feedback technique: given a query, we determine its topic by classifying the Web search results retrieved by the query. Motivated by the needs of search advertising, we primarily focus on rare queries, which are the hardest from the point of view of machine learning, yet in aggregate account for a considerable fraction of search engine traffic. Empirical evaluation confirms that our methodology yields a considerably higher classification accuracy than previously reported. We believe that the proposed methodology will lead to better matching of online ads to rare queries and overall to a better user experience.