BERT Sentence Embeddings trained on Wikipedia and BooksCorpus and fine-tuned on QNLI


This model uses a BERT base architecture initialized from and fine-tuned on QNLI. This is a BERT base architecture but some changes have been made to the original training and export scheme based on more recent learnings.

This model is intended to be used for a variety of English NLP tasks. The pre-training data contains more formal text and the model may not generalize to more colloquial text such as social media or messages.

This model is fine-tuned on the QNLI and is recommended for use in question-based natural language inference tasks. The QNLI fine-tuning task where is a classification task for a question, context pair, whether the context contains the answer and where the context paragraphs are drawn from Wikipedia.


How to use

sent_embeddings = BertSentenceEmbeddings.pretrained("sent_bert_wiki_books_qnli", "en") \
      .setInputCols("sentence") \

nlp_pipeline = Pipeline(stages=[document_assembler, sentence_detector, sent_embeddings ])
val sent_embeddings = BertSentenceEmbeddings.pretrained("sent_bert_wiki_books_qnli", "en")

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

text = ["I love NLP"]
sent_embeddings_df = nlu.load('en.embed_sentence.bert.wiki_books_qnli').predict(text, output_level='sentence')

Model Information

Model Name: sent_bert_wiki_books_qnli
Compatibility: Spark NLP 3.2.0+
License: Open Source
Edition: Official
Input Labels: [sentence]
Output Labels: [bert_sentence]
Language: en
Case sensitive: false

Data Source

This Model has been imported from: