BERT Sentence Embeddings trained on Wikipedia and BooksCorpus and fine-tuned on SST-2

Description

This model uses a BERT base architecture initialized from https://tfhub.dev/google/experts/bert/wiki_books/1 and fine-tuned on SST-2. 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 SST-2 and is recommended for use in sentiment analysis tasks. The fine-tuning task uses the Stanford Sentiment Treebank (SST-2) dataset to predict the sentiment in a given sentence.

Live Demo Open in Colab Download Copy S3 URI

How to use

sent_embeddings = BertSentenceEmbeddings.pretrained("sent_bert_wiki_books_sst2", "en") \
.setInputCols("sentence") \
.setOutputCol("bert_sentence")

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

val sent_embeddings = BertSentenceEmbeddings.pretrained("sent_bert_wiki_books_sst2", "en")
.setInputCols("sentence")
.setOutputCol("bert_sentence")

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_sst2').predict(text, output_level='sentence')
sent_embeddings_df

Model Information

Data Source

This Model has been imported from: https://tfhub.dev/google/experts/bert/wiki_books/sst2/2