Icon

Multalabel_​classification_​complaints_​case

Go to Product
Multi-label text classification with Redfield NLP Nodes

The example of applying Redfield NLP Nodes for multi-label text classification. In the workflow shown a case with bank customers complaints written as a plain text. Each of the complaint contain 2 tags: Issue and Sub-issue. The trained model assigns multiple tags, model estimation is based on Jaccard coefficient.

The extension can be obtained here: https://nlpnodes.com/

Download a modefrom repositoryGet statisticson the texts lengthTrainingValidationTrain multi-labelclassifierClasses distributionTraining + ValidationTestApply to test dataPredictions analysisCombine labelsSimple textprocessingRead the dataBERT Model Selector Text assessment Partitioning BERT Multi-labelClassification Learner Bar Chart Partitioning BERT Predictor Multilabel resultsvisualization Column Aggregator String Manipulation Table Reader Download a modefrom repositoryGet statisticson the texts lengthTrainingValidationTrain multi-labelclassifierClasses distributionTraining + ValidationTestApply to test dataPredictions analysisCombine labelsSimple textprocessingRead the dataBERT Model Selector Text assessment Partitioning BERT Multi-labelClassification Learner Bar Chart Partitioning BERT Predictor Multilabel resultsvisualization Column Aggregator String Manipulation Table Reader

Nodes

Extensions

Links