Russian BertForSequenceClassification Base Cased model (from cointegrated)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. rubert-base-cased-nli-threeway is a Russian model originally trained by cointegrated.

Predicted Entities

neutral, contradiction, entailment

Download Copy S3 URI

How to use

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

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

sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_ru_base_cased_nli_threeway","ru") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

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

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

result = pipeline.fit(data).transform(data)

val documentAssembler = new DocumentAssembler()
    .setInputCol("text")
    .setOutputCol("document")

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

val sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_ru_base_cased_nli_threeway","ru")
    .setInputCols(Array("document", "token"))
    .setOutputCol("ner")

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

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

val result = pipeline.fit(data).transform(data)

Model Information

Model Name:	bert_sequence_classifier_ru_base_cased_nli_threeway
Compatibility:	Spark NLP 4.3.1+
License:	Open Source
Edition:	Official
Input Labels:	[document, token]
Output Labels:	[ner]
Language:	ru
Size:	667.1 MB
Case sensitive:	true
Max sentence length:	128

References

https://huggingface.co/cointegrated/rubert-base-cased-nli-threeway
https://github.com/felipessalvatore/NLI_datasets
https://github.com/sheng-z/JOCI
https://cims.nyu.edu/~sbowman/multinli/
https://aclanthology.org/I17-1011/
http://www.lrec-conf.org/proceedings/lrec2014/pdf/363_Paper.pdf
https://nlp.stanford.edu/projects/snli/
https://github.com/facebookresearch/anli
https://github.com/easonnie/combine-FEVER-NSMN/blob/master/other_resources/nli_fever.md
https://github.com/facebookresearch/Imppres
https://cs.brown.edu/people/epavlick/papers/ans.pdf
https://people.ict.usc.edu/~gordon/copa.html
https://aclanthology.org/I17-1100
https://allenai.org/data/scitail
https://github.com/felipessalvatore/NLI_datasets
https://github.com/verypluming/HELP
https://github.com/atticusg/MoNLI
https://russiansuperglue.com/ru/tasks/task_info/TERRa

PREVIOUSEnglish BertForSequenceClassification Cased model (from vinaydngowda)

NEXTRussian BertForSequenceClassification Base Cased model (from cointegrated)