Description
This pretrained pipeline is built on the top of bert_sequence_classifier_trec_coarse_en.
The TREC dataset for question classification consists of open-domain, fact-based questions divided into broad semantic categories. You can check the official documentation of the dataset, entities, etc. here.
How to use
trec_pipeline = PretrainedPipeline("bert_sequence_classifier_trec_coarse_pipeline", lang = "en")
trec_pipeline.annotate("Germany is the largest country in Europe economically.")
val trec_pipeline = new PretrainedPipeline("bert_sequence_classifier_trec_coarse_pipeline", lang = "en")
trec_pipeline.annotate("Germany is the largest country in Europe economically.")
Results
['LOC']
Model Information
| Model Name: | bert_sequence_classifier_trec_coarse_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 3.4.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 406.6 MB |
Included Models
- DocumentAssembler
- TokenizerModel
- BertForSequenceClassification