| C02-1101 | elements using min-max modular | neural networks | . Compared to their method , |
| C02-1081 | input was classified by trained | neural networks | with varying error rates depending |
| C02-1087 | documents to numeric vectors . Often | neural networks | including the SOM model for text |
| C04-1076 | investigated by using models of | neural networks | . In their succeeding work ( |
| C90-3036 | task tractable with distributed | neural networks | . The scale-up prospects of the |
| C90-3036 | input to the next network , and | neural networks | in general tolerate , even filter |
| A94-1003 | . Batchelder ( 1992 ) trained | neural networks | to recognize 3-6 character words |
| C00-2145 | austere approach where lie uses | neural networks | ( NN ) to translate surface strings |
| C04-1201 | avoid the over-fitting problems of | neural networks | as they are based on the structural |
| C90-2067 | Disambiguation with Very Large | Neural Networks | Extracted from Machine Readable |
| A00-1022 | Joachims , 1998 ) . Neural Networks : | Neural Networks | are a special kind of " non-symbolic |
| C02-1101 | a learning model ( boosting or | neural networks | ) to learn as corpus errors . |
| A00-2035 | classifiers ( decision trees and | neural networks | ) to make the predictions . This |
| C02-1081 | discriminate between speaker classes . | Neural networks | were used for automatic classifica |
| C00-2145 | extract rules from the trained | neural networks | seek to isolate and make explicit |
| C90-2067 | than one word at a time . 2.2 . | Neural networks | for WSD Neural network approaches |
| A00-2009 | approach where the output from two | neural networks | is combined ; one network is |
| A00-1022 | SVM_Light ( Joachims , 1998 ) . | Neural Networks | : Neural Networks are a special |
| A97-1003 | Conclusion We have shown that using | neural networks | for automatically segmenting |
| C90-2071 | including markeropassing models and | neural networks | of both the connectionist and |
