Context Training Training Cross Testing

Table 3: Results of comparing hidden layer sizes (6-context). Training was done on 573 items, using a cross validation set of 258 items. and perhaps even to other markup recognition problems , and (iv) compare the use of the neural net with more conventional tools such as decision trees and Hidden Markov Models. for assistance in nding references and determining the status of related work. Special thanks to Prof. Franz Guenthner for introducing us to the problem. 6 Sharp). Also included in this group are items such as U.S. Supreme Court or U.S. Army, which are sometimes mislabeled because U.S. occurs very frequently at the end of a sentence as well. 22.5% false negative due to an abbreviation at the end of a sentence, most frequently Inc., Co., Corp., or U.S., which all occur within sentences as well. 11.0% false positive or negative due to a sequence of characters including a punctuation mark and quotation marks, as this sequence can occur both within and at the end of sentences. 9.2% false negative resulting from an abbreviation followed by quotation marks; related to the previous two types. 9.8% false positive or false negative resulting from presence of ellipsis (...), which can occur at the end of or within a sentence. 9.9% miscellaneous errors, including extraneous characters (dashes, asterisks, etc.), un-grammatical sentences, misspellings, and parenthetical sentences. The results presented above (409 errors) are obtained when both t 0 and t 1 are set at 0:5. Adjusting the sensitivity thresholds decreases the number of punctuation marks which are mislabeled by the method. For example, when the upper threshold is set at 0:8 and the lower threshold at 0:2, the network places 164 items between the two. Thus when the algorithm does not have enough evidence to classify the items, some mislabeling can be avoided. 5 We also experimented with diierent context sizes and numbers of hidden units, obtaining the results shown in Tables 2 and 3. All results were found using the same training set of 573 items, cross-validation set of 258 items, and mixed-case test set of 27,294 items. The \Training Error" is one-half the sum of all the errors for all 573 items in the training set, where the \error" is the diierence between the desired output and the actual output of the neural net. The \Cross Error" is the equivalent value for the cross-validation set. These two error gures give …