README.md

metadata

language:
  - code
tags:
  - question-answering
  - knowledge-graph

SPBERT MLM (Initialized)

Introduction

Paper: SPBERT: An Efficient Pre-training BERT on SPARQL Queries for Question Answering over Knowledge Graphs Authors: Hieu Tran, Long Phan, James Anibal, Binh T. Nguyen, Truong-Son Nguyen

How to use

For more details, do check out our Github repo. Here is an example in Pytorch:

from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained('razent/spbert-mlm-base')
model = AutoModel.from_pretrained("razent/spbert-mlm-base")
text = "select * where brack_open var_a var_b var_c sep_dot brack_close"
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)

or Tensorflow

from transformers import AutoTokenizer, TFAutoModel
tokenizer = AutoTokenizer.from_pretrained('razent/spbert-mlm-base')
model = TFAutoModel.from_pretrained("razent/spbert-mlm-base")
text = "select * where brack_open var_a var_b var_c sep_dot brack_close"
encoded_input = tokenizer(text, return_tensors='tf')
output = model(encoded_input)

Citation

@misc{tran2021spbert,
      title={SPBERT: An Efficient Pre-training BERT on SPARQL Queries for Question Answering over Knowledge Graphs}, 
      author={Hieu Tran and Long Phan and James Anibal and Binh T. Nguyen and Truong-Son Nguyen},
      year={2021},
      eprint={2106.09997},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}