"... In PAGE 14: ... We will examine four rainbow options: a call spread, an outperformance option, a call worst, and a basket. Table2 shows the payoff function for each. In addition to choosing a particular rainbow option, we must choose a strike price.... In PAGE 16: ... Different rainbow options have different relative sensitivities to correlation and volatility, creating some variation in how well the option package methodology can remove the sensitivity to volatility. To choose a particular rainbow option to use in our empirical application, we repeat our simulations of the option package methodology with the three remaining rainbow options from Table2 and compare the results. Table 5 presents results using an outperformance option.... ..."

"... In PAGE 51: ...12 Conclusions Tables 2, 3, 4 and 5 present a comparative analysis of the systems. In Table2 we characterize as complete systems, systems that, in addition to providing an integration framework and a transaction model, support network communication and various operating system facilities. Thor is di erent from the other systems described in that it does not support the integration of pre-existing systems.... ..."

"... In PAGE 5: ...fter selecting a set of features f1....fn and optionally smooth- ing their probabilities, we must assign them scores, used to place test documents in the set of positive reviews C or negative reviews Cprime. We tried some machine-learning techniques using the Rainbow text-classification package [10], but Table9 shows the performance was no better than our method. We also tried SVMlight, the package2 used by Pang et.... ..."

"... In PAGE 5: ...6 Scoring After selecting a set of features a75 a37a18a76a16a76a16a76a16a76 a75 a28 and optionally smooth- ing their probabilities, we must assign them scores, used to place test documents in the set of positive reviews a3 or negative reviews a3 a10 . We tried some machine-learning techniques using the Rainbow text-classification package [11], but Table9 shows the performance was no better than our method. We also tried SVMa12a14a13a16a15a18a17a20a19 , the package2 used by Pang et al.... ..."

"... In PAGE 7: ...Table 9: Rainbow accuracy with word bigrams. Table9 shows the average accuracy of the Rainbow word bigram classifiers using the same 20-fold cross-validation setup as in the previous experiments. As we expected, using word bi- grams rather than parse label unigrams improved the performance of the Rainbow classifiers.... ..."

"... In PAGE 5: ... For instance, a META tag content cannot directly be used to classify a hyperlink, since the relation of a META tag (being a special class of HTML document fragment) to a hyperlink is only intermediated by a whole HTML document. Table1 demonstrates how the four-dimensional space of the TODD model can be visualised, on the example of services implemented within the Rain- bow applications mentioned in section 3. Rows correspond to object types and columns to data/representation types.... ..."