>>> git clone https://github.com/UKPLab/sentence-transformers.git --branch v0.3.3
>>> cd sentence-transformers/
>>> pip install -e .

>>> pip install sentence-transformers==0.3.3

>>> cd 
   
    
>>> wget https://storage.googleapis.com/phrase-bert/phrase-bert/phrase-bert-model.zip
>>> unzip phrase-bert-model.zip -d phrase-bert-model/
>>> rm phrase-bert-model.zip

   

from sentence_transformers import SentenceTransformer
model_path = '
   
    '
model = SentenceTransformer(model_path)

   

phrase_list = [ 'play an active role', 'participate actively', 'active lifestyle']
phrase_embs = model.encode( phrase_list )
[p1, p2, p3] = phrase_embs

for phrase, embedding in zip(phrase_list, phrase_embs):
    print("Phrase:", phrase)
    print("Embedding:", embedding)
    print("")

import numpy as np
print(f'The dot product between phrase 1 and 2 is: {np.dot(p1, p2)}')
print(f'The dot product between phrase 1 and 3 is: {np.dot(p1, p3)}')
print(f'The dot product between phrase 2 and 3 is: {np.dot(p2, p3)}')

import torch 
from torch import nn
cos_sim = nn.CosineSimilarity(dim=0)
print(f'The cosine similarity between phrase 1 and 2 is: {cos_sim( torch.tensor(p1), torch.tensor(p2))}')
print(f'The cosine similarity between phrase 1 and 3 is: {cos_sim( torch.tensor(p1), torch.tensor(p3))}')
print(f'The cosine similarity between phrase 2 and 3 is: {cos_sim( torch.tensor(p2), torch.tensor(p3))}')

The dot product between phrase 1 and 2 is: 218.43600463867188
The dot product between phrase 1 and 3 is: 165.48483276367188
The dot product between phrase 2 and 3 is: 160.51708984375
The cosine similarity between phrase 1 and 2 is: 0.8142536282539368
The cosine similarity between phrase 1 and 3 is: 0.6130303144454956
The cosine similarity between phrase 2 and 3 is: 0.584893524646759

export INPUT_DATA_PATH=
   
    
export TRAIN_DATA_FILE=
    
     
export VALID_DATA_FILE=
     
      
export INPUT_MODEL_PATH=bert-base-nli-stsb-mean-tokens 
export OUTPUT_MODEL_PATH=
      
       


python -u phrase_bert_finetune.py \
    --input_data_path $INPUT_DATA_PATH \
    --train_data_file $TRAIN_DATA_FILE \
    --valid_data_file $VALID_DATA_FILE \
    --input_model_path $INPUT_MODEL_PATH \
    --output_model_path $OUTPUT_MODEL_PATH

      
     
    
   

@inproceedings{phrasebertwang2021,
    author={Shufan Wang and Laure Thompson and Mohit Iyyer},
    Booktitle = {Empirical Methods in Natural Language Processing},
    Year = "2021",
    Title={Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration}
}