Description
Pretrained RoBERTa Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. roberta-large-bne is a Spanish model orginally trained by PlanTL-GOB-ES.
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")
embeddings = RoBertaEmbeddings.pretrained("roberta_embeddings_roberta_large_bne","es") \
.setInputCols(["document", "token"]) \
.setOutputCol("embeddings")
pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])
data = spark.createDataFrame([["Me encanta chispa nlp"]]).toDF("text")
result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = new Tokenizer()
.setInputCols(Array("document"))
.setOutputCol("token")
val embeddings = RoBertaEmbeddings.pretrained("roberta_embeddings_roberta_large_bne","es")
.setInputCols(Array("document", "token"))
.setOutputCol("embeddings")
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
val data = Seq("Me encanta chispa nlp").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("es.embed.roberta_large_bne").predict("""Me encanta chispa nlp""")
Model Information
| Model Name: | roberta_embeddings_roberta_large_bne |
| Compatibility: | Spark NLP 3.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [bert] |
| Language: | es |
| Size: | 848.5 MB |
| Case sensitive: | true |
References
- https://huggingface.co/PlanTL-GOB-ES/roberta-large-bne
- https://arxiv.org/abs/1907.11692
- http://www.bne.es/en/Inicio/index.html
- http://www.bne.es/en/Inicio/index.html
- https://arxiv.org/abs/1907.11692
- https://github.com/PlanTL-GOB-ES/lm-spanish
- https://arxiv.org/abs/2107.07253