Edit on GitHub
  • John Snow Labs
  • Sep 15, 2021

BERT Sentence Embeddings German (Base Cased)

  • open_source
  • bert_sentence_embeddings
  • de

Description

BERT model trained in German language on a 16GB dataset comprising of Wikipedia dump, EU Bookshop corpus, Open Subtitles, CommonCrawl, ParaCrawl and News Crawl in an MLM fashion.

Predicted Entities

Download Copy S3 URI

How to use

sent_embeddings = BertSentenceEmbeddings.pretrained("sent_bert_base_cased", "de") \
.setInputCols("sentence") \
.setOutputCol("bert_sentence")

nlp_pipeline = Pipeline(stages=[document_assembler, sentence_detector, sent_embeddings ])

val sent_embeddings = BertSentenceEmbeddings.pretrained("sent_bert_base_cased", "de")
.setInputCols("sentence")
.setOutputCol("bert_sentence")

val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, sent_embeddings ))

import nlu
nlu.load("de.embed_sentence.bert.base_cased").predict("""Put your text here.""")

Results

768 dimensional embedding vector per sentence.

Model Information

Model Name: sent_bert_base_cased
Compatibility: Spark NLP 3.2.2+
License: Open Source
Edition: Official
Input Labels: [sentence]
Output Labels: [bert_sentence]
Language: de
Case sensitive: true

Data Source

This model is imported from https://huggingface.co/dbmdz/bert-base-german-cased