Metadata-Version: 2.1
Name: underthesea_core
Version: 0.0.5_alpha.1
Summary: Underthesea Core (fast & fun)
Home-Page: https://github.com/undertheseanlp/underthesea/
Author: Vu Anh <anhv.ict91@gmail.com>
Author-Email: Vu Anh <anhv.ict91@gmail.com>
License: GPL-3.0
Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM

# Underthesea Core (fast & fun)

## Usage

CRFFeaturizer

```python
>>> from underthesea_core import CRFFeaturizer
>>> features = ["T[-1]", "T[0]", "T[1]"]
>>> dictionary = set(["sinh viên"])
>>> featurizer = CRFFeaturizer(features, dictionary)
>>> sentences = [[["sinh", "X"], ["viên", "X"], ["đi", "X"], ["học", "X"]]]
>>> featurizer.process(sentences)
[[['T[-1]=BOS', 'T[0]=sinh', 'T[1]=viên'],
  ['T[-1]=sinh', 'T[0]=viên', 'T[1]=đi'],
  ['T[-1]=viên', 'T[0]=đi', 'T[1]=học'],
  ['T[-1]=đi', 'T[0]=học', 'T[1]=EOS']]]
```

