English BertForSequenceClassification Cased model (from ndavid)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. autotrain-trec-fine-bert-739422530 is a English model originally trained by ndavid.

Predicted Entities

lang, cremat, speed, product, instru, religion, desc, manner, mount, dist, body, color, exp, def, sport, perc, dismed, other, ord, weight, count, food, currency, veh, volsize, techmeth, money, ind, word, substance, period, state, gr, code, plant, animal, date, symbol, title, abb, city, event, country, termeq, reason, temp, letter

Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("document")

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")

seq_classifier = BertForSequenceClassification.pretrained("bert_classifier_autotrain_trec_fine_739422530","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

pipeline = Pipeline(stages=[documentAssembler, tokenizer, seq_classifier])

data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")

result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler()
      .setInputCols(Array("text"))
      .setOutputCols(Array("document"))

val tokenizer = new Tokenizer()
    .setInputCols("document")
    .setOutputCol("token")

val seq_classifier = BertForSequenceClassification.pretrained("bert_classifier_autotrain_trec_fine_739422530","en")
    .setInputCols(Array("document", "token"))
    .setOutputCol("class")

val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, seq_classifier))

val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text")

val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.classify.bert.by_ndavid").predict("""PUT YOUR STRING HERE""")

Model Information

Model Name: bert_classifier_autotrain_trec_fine_739422530
Compatibility: Spark NLP 4.1.0+
License: Open Source
Edition: Official
Input Labels: [document, token]
Output Labels: [class]
Language: en
Size: 410.2 MB
Case sensitive: true
Max sentence length: 256

References

  • https://huggingface.co/ndavid/autotrain-trec-fine-bert-739422530