Kohonen Network Modeling for Lemma Recognition in Bangka Dialect of Malay

There are numbers of lemmas in the Bangka Dialect of Malay (BDoM) Dictionary. However, tracking the lemmas that have been used before is an impractical work because there are thousands of lemmas that must be traced one by one. This research intends to minimize the search burden of many lemma data using the Kohonen network. By using the Kohonen network, it is sufficient to do training on the sample data provided which is far less than the actual data. The result of this training is then used to obtain the number of lemmas that are successfully identified by the Kohonen network. The result can also be used to propose a lemma so that the status of acceptance of the proposed lemma can be determined. The overall result that is variable is obtained because of the optimization used. From the test result, it is also found that there is no linear relationship between the level of learning rate and the number of names that were successfully identified. Further research that can be done are the inclusion of non-BDoM lemma training data, changing Kohonen network parameters, or using other recognition methods.