We study information theoretic methods for ranking biomarkers. In clinical trials there are two, closely related, types of biomarkers: predictive and prognostic, and disentangling them is a key challenge. Our first step is to phrase biomarker ranking in terms of optimizing an information theoretic quantity. This formalization of the problem will enable us to derive rankings of predictive/progno...

Group consensus ranking is an important topic in performance evaluation and selection research. Data envelopment analysis (DEA) has been used for obtaining an efficiency score (preference score) for each candidate. We propose an integrated DEA and simulation method for group consensus ranking. The ranking method proposed in this study has several unique features. In contrast to most voting meth...

Evaluating text fragments for positive and negative subjective expressions and their strength can be important in applications such as singleor multidocument summarization, document ranking, data mining, etc. This paper looks at a simplified version of the problem: classifying online product reviews into positive and negative classes. We discuss a series of experiments with different machine le...

We describe in this paper our system for the Prior-art task of CLEFIP 2010 (a task focused on the retrieval of relevant patents to a given one) and its results. We have developed a system where patents are indexed by fields in order to allow a selection of the most discriminative terms of each field, applying Kullback-Leibler divergence as feature selection method, and using different boost fac...

The goal of this project is to build a Contextual Suggestion system that will recommend the user a ranked list of suggestions depending on user's context as well as her preferences. In this context we present an algorithm based on the regular expression for extracting time and address information from different websites for the places. Then we have suggested a ranking function that can utilize ...

We argue that ranking algorithms for XML should reflect the actual combined content and structure constraints of queries, while at the same time producing equal rankings for queries that are semantically equal. Ranking algorithms that produce different rankings for queries that are semantically equal are easily detected by tests on large databases: We call such algorithms not sound. We report t...

Although every terminating loop has a ranking function, not every loop has a ranking function of a restricted form, such as a lexicographic tuple of polynomials over program variables. The polyranking principle is proposed as a generalization of polynomial ranking for analyzing termination of loops. We define lexicographic polyranking functions in the context of loops with parallel transitions ...

A method for data-driven lexical adaptation on the basis of a limited number of acoustic training tokens is discussed. The method is closely related to pronunciation modeling techniques. A set of pronunciation variants is generated by forced alignment, followed by a step to select promising pronunciation candidates by using a ranking function. The method has been validated on a database consist...

Despite the increase in recent years in the portfolio of addedvalue chemicals that can be microbially produced, the design process still remains a complex system, costly and rather slow. To overcome such limitations, the development of Computer-Aided-Design (CAD) tools is necessary to design production pathway that systematically screen metabolic databases to select best genes to import into ch...

With the increase in the use of mark-up languages, a new scenario has raised into the IR field; this new scenario is focused on structured documents, and has been defined as structured IR. The classic IR models have been extended in order to be applied to this new scenario. Generally these adaptations have been carried on by weighting the fields that form the document structure, and making the ...