Skip to main content

A tool for converting raw text to slot

Project description

bert_slot_tokenizer

Version 0.2

Travis (.org) GitHub

bert_slot_tokenizer 是一个将slot filling 任务中slot解析为其他格式的工具

环境:

  • Python 3
  • Python 2

安装:

pip install bert-slot-tokenizer

支持的格式:

使用方法:

from bert_slot_tokenizer import SlotConverter
vacab_path = 'tests/test_data/example_vocab.txt' 
# you can find a example here --> https://github.com/DevRoss/bert-slot-tokenizer/blob/master/tests/test_data/example_vocab.txt
sc = SlotConverter(vocab_path, do_lower_case=True)
text = 'Too YOUNG, too simple, sometimes naive! 蛤蛤+1s'
slot = {'name': '蛤蛤', 'time': '+1s'}
output_text, iob_slot = sc.convert2iob(text, slot)
print(output_text)
# ['too', 'young', ',', 'too', 'simple', ',', 'some', '##times', 'na', '##ive', '!', '蛤', '蛤', '+', '1', '##s']
print(iob_slot)
# ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-name', 'I-name', 'B-time', 'I-time', 'I-time']

写在最后:

感谢BERT对NLP领域的推动

感谢开源

欢迎PR和issue

联系方式: devross1997@gmail.com

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

bert_slot_tokenizer-0.2.1.tar.gz (11.9 kB view hashes)

Uploaded Source

Built Distribution

bert_slot_tokenizer-0.2.1-py2.py3-none-any.whl (13.1 kB view hashes)

Uploaded Python 2 Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page