Spanish Named Entity Recognition, (RoBERTa base trained with data from the National Library of Spain (BNE) and CONLL 2003 data), by the TEMU Unit of the BSC-CNS

Description

Pretrained Named Entity Recognition model, uploaded to Hugging Face, adapted and imported into Spark NLP. roberta-base-bne-conll-ner_spark_nlp is a Spanish model orginally trained by TEMU-BSC for PlanTL-GOB-ES.

Predicted Entities

Live Demo Open in Colab Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler()
.setInputCol(“text”)
.setOutputCol(“document”)

sentenceDetector = SentenceDetector()
.setInputCols([“document”])
.setOutputCol(“sentence”)

tokenizer = Tokenizer()
.setInputCols(“sentence”)
.setOutputCol(“token”)

ner = RoBertaForTokenClassification.pretrained(“roberta_base_bne_conll_ner_spark_nlp”,”es”)
.setInputCols([“sentence”, “token”])
.setOutputCol(“ner”)

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

data = spark.createDataFrame([[“El Plan Nacional para el Impulso de las Tecnologías del Lenguage es una iniciativa del Gobierno de España”]]).toDF(“text”)

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

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

sentenceDetector = SentenceDetector()\
.setInputCols(["document"])\
.setOutputCol("sentence")

tokenizer = Tokenizer() \
    .setInputCols("sentence") \
    .setOutputCol("token")
  
ner = RoBertaForTokenClassification.pretrained("roberta_base_bne_conll_ner_spark_nlp","es") \
    .setInputCols(["sentence", "token"]) \
    .setOutputCol("ner")
    
pipeline = Pipeline(stages=[documentAssembler, tokenizer, ner])

data = spark.createDataFrame([["El Plan Nacional para el Impulso de las Tecnologías del Lenguage es una iniciativa del Gobierno de España"]]).toDF("text")

Model Information