Skip to content

README.en

Jump to bottom
km1994 edited this page Jan 19, 2021 · 1 revision

alt text

PyPI version Contributions welcome License Apache 2.0 Language Python3

pycorrector

Chinese Text Error Correction Tool.

pycorrector Use the language model to detect errors, pinyin feature and shape feature to correct chinese text error, it can be used for Chinese Pinyin and stroke input method.

Features

language model

  • Kenlm
  • RNNLM

deep model

  • rnn_attention
  • seq2seq_attention
  • conv_seq2seq
  • transformer
  • bert
  • electra

Install

  • auto：pip install pycorrector
  • manual：
git clone https://github.com/shibing624/pycorrector.git
cd pycorrector
python setup.py install

Install Requires

  • install kenlm
pip install https://github.com/kpu/kenlm/archive/master.zip
  • install others
pip install -r requirements.txt

Usage

  • Text Correction
import pycorrector

corrected_sent, detail = pycorrector.correct('少先队员因该为老人让坐')
print(corrected_sent, detail)

output:

少先队员应该为老人让座 [[('因该', '应该', 4, 6)], [('坐', '座', 10, 11)]]

model load from: ~/.pycorrector/datasets/zh_giga.no_cna_cmn.prune01244.klm, if not download auto, do it from file(2.8G).Correction

  • Error Detection
import pycorrector

idx_errors = pycorrector.detect('少先队员因该为老人让坐')
print(idx_errors)

output:

[['因该', 4, 6, 'word'], ['坐', 10, 11, 'char']]

return list, [error_word, begin_pos, end_pos, error_type]，pos index starts with 0.

  • English Seplling Error Correction
import pycorrector

sent_lst = ['what', 'hapenning', 'how', 'to', 'speling', 'it', 'you', 'can', 'gorrect', 'it']
for i in sent_lst:
    print(i, '=>', pycorrector.en_correct(i))

output:

what => what
hapenning => happening
how => how
to => to
speling => spelling
it => it
you => you
can => can
gorrect => correct
it => it

Command Line Usage

  • Command line
python -m pycorrector -h
usage: __main__.py [-h] -o OUTPUT [-n] [-d] input

@description:

positional arguments:
  input                 the input file path, file encode need utf-8.

optional arguments:
  -h, --help            show this help message and exit
  -o OUTPUT, --output OUTPUT
                        the output file path.
  -n, --no_char         disable char detect mode.
  -d, --detail          print detail info

case：

python -m pycorrector input.txt -o out.txt -n -d

input file：input.txt; output file：out.txt

Future work

  1. P(c), the language model. We could create a better language model by collecting more data, and perhaps by using a little English morphology (such as adding "ility" or "able" to the end of a word).

  2. P(w|c), the error model. So far, the error model has been trivial: the smaller the edit distance, the smaller the error. Clearly we could use a better model of the cost of edits. get a corpus of spelling errors, and count how likely it is to make each insertion, deletion, or alteration, given the surrounding characters.

  3. It turns out that in many cases it is difficult to make a decision based only on a single word. This is most obvious when there is a word that appears in the dictionary, but the test set says it should be corrected to another word anyway: correction('where') => 'where' (123); expected 'were' (452) We can't possibly know that correction('where') should be 'were' in at least one case, but should remain 'where' in other cases. But if the query had been correction('They where going') then it seems likely that "where" should be corrected to "were".

  4. Finally, we could improve the implementation by making it much faster, without changing the results. We could re-implement in a compiled language rather than an interpreted one. We could cache the results of computations so that we don't have to repeat them multiple times. One word of advice: before attempting any speed optimizations, profile carefully to see where the time is actually going.

Further Reading

Cite

@software{pycorrector,
  author = {Xu Ming},
  title = {{pycorrector: Text Error Correction Tool}},
  year = {2020},
  url = {https://github.com/shibing624/pycorrector},
}

License

Apache License 2.0

References

Clone this wiki locally