Description
Pretrained ALBERT Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. ALR_BERT is a Romanian model orginally trained by dragosnicolae555.
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")
embeddings = AlbertEmbeddings.pretrained("albert_embeddings_ALR_BERT","ro") \
.setInputCols(["document", "token"]) \
.setOutputCol("embeddings")
pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])
data = spark.createDataFrame([["Îmi place Spark 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 = AlbertEmbeddings.pretrained("albert_embeddings_ALR_BERT","ro")
.setInputCols(Array("document", "token"))
.setOutputCol("embeddings")
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
val data = Seq("Îmi place Spark NLP").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("ro.embed.ALR_BERT").predict("""Îmi place Spark NLP""")
Model Information
| Model Name: | albert_embeddings_ALR_BERT |
| Compatibility: | Spark NLP 3.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [bert] |
| Language: | ro |
| Size: | 54.5 MB |
| Case sensitive: | false |
References
- https://huggingface.co/dragosnicolae555/ALR_BERT