Icon

Multalabel_​classification_​complaints_​case

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

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: artemryasik
Created at: 2021-09-14
On NodePit since: 2021-10-15
Last update: 2024-04-23
Created with KNIME version: v4.4.1
Tags: RedfieldBERTNLPMulti-label classificationText classification
NodePit Exclusive Only available on NodePit

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!