Description
Legal Bert-based Question Answering model, trained on squad-v2, finetuned on proprietary Legal questions and answers.
Predicted Entities
How to use
documentAssembler = nlp.MultiDocumentAssembler()\
.setInputCols(["question", "context"])\
.setOutputCols(["document_question", "document_context"])
spanClassifier = nlp.BertForQuestionAnswering.pretrained("legqa_bert","en", "legal/models") \
.setInputCols(["document_question", "document_context"]) \
.setOutputCol("answer") \
.setCaseSensitive(True)
pipeline = nlp.Pipeline().setStages([
documentAssembler,
spanClassifier
])
example = spark.createDataFrame([["Who was subjected to torture?", "The applicant submitted that her husband was subjected to treatment amounting to abuse whilst in the custody of police."]]).toDF("question", "context")
result = pipeline.fit(example).transform(example)
result.select('answer.result').show()
Results
`her husband`
Model Information
| Model Name: | legqa_bert |
| Compatibility: | Legal NLP 1.0.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [document_question, document_context] |
| Output Labels: | [answer] |
| Language: | en |
| Size: | 407.9 MB |
| Case sensitive: | true |
| Max sentence length: | 512 |
References
Trained on squad-v2, finetuned on proprietary Legal questions and answers.