Description
This model provides 200-dimensional pre-trained word embeddings trained on the 2024 Wikipedia and Gigaword 5 corpora (11.9B tokens, 1.2M vocabulary).
How to use
from sparknlp.base import *
from sparknlp.annotator import *
from pyspark.ml import Pipeline
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols(["document"]) \
.setOutputCol("token")
embeddings_loaded = WordEmbeddingsModel.pretrained("./glove2024_wikigiga_200d")\
.setInputCols(["document", "token"])\
.setOutputCol("embeddings")
embeddingsFinisher = EmbeddingsFinisher() \
.setInputCols(["embeddings"]) \
.setOutputCols("finished_embeddings") \
.setOutputAsVector(True) \
.setCleanAnnotations(False)
pipeline = Pipeline() \
.setStages([
documentAssembler,
tokenizer,
embeddings_loaded,
embeddingsFinisher
])
data = spark.createDataFrame([["This is a test sentence for an embedding model"]]).toDF("text")
result = pipeline.fit(data).transform(data)
result.select("finished_embeddings").show(truncate=False)
import com.johnsnowlabs.nlp._
import com.johnsnowlabs.nlp.annotators._
import org.apache.spark.ml.Pipeline
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = new Tokenizer()
.setInputCols("document")
.setOutputCol("token")
val embeddings_loaded = WordEmbeddingsModel
.pretrained("./glove2024_wikigiga_200d")
.setInputCols("document", "token")
.setOutputCol("embeddings")
val embeddingsFinisher = new EmbeddingsFinisher()
.setInputCols("embeddings")
.setOutputCols("finished_embeddings")
.setOutputAsVector(true)
.setCleanAnnotations(false)
val pipeline = new Pipeline().setStages(Array(
documentAssembler,
tokenizer,
embeddings_loaded,
embeddingsFinisher
))
val data = Seq("This is a test sentence for an embedding model").toDF("text")
val result = pipeline.fit(data).transform(data)
result.select("finished_embeddings").show(false)
Results
+-------------------------------+
| embeddings |
+-------------------------------+
|[[-0.08433199673891068, -0.2...|
+-------------------------------+
Model Information
| Model Name: | glove2024_wikigiga_200d |
| Type: | embeddings |
| Compatibility: | Spark NLP 6.0.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [embeddings] |
| Language: | en |
| Size: | 974.1 MB |
| Case sensitive: | false |
| Dimension: | 200 |