資源簡介
# 中文命名實體識別
基于條件隨機場（Conditional Random Field, CRF)的NER模型
## 數據集
數據集用的是論文ACL 2018[Chinese NER using Lattice LSTM](https://github.com/jiesutd/LatticeLSTM)中收集的簡歷數據，數據的格式如下，它的每一行由一個字及其對應的標注組成，標注集采用BIOES，句子之間用一個空行隔開。
```
美 B-LOC
國 E-LOC
的 O
華 B-PER
萊 I-PER
士 E-PER
代碼片段和文件信息
from?sklearn_crfsuite?import?CRF
class?CRFModel（object）:
????def?__init__（self
?????????????????algorithm=‘lbfgs‘
?????????????????c1=0.1
?????????????????c2=0.1
?????????????????max_iterations=100
?????????????????all_possible_transitions=False
?????????????????）:
????????self.model?=?CRF（algorithm=algorithm
?????????????????????????c1=c1
?????????????????????????c2=c2
?????????????????????????max_iterations=max_iterations
?????????????????????????all_possible_transitions=all_possible_transitions）
????def?train（self?sentences?tag_lists）:
????????features?=?[self.sent2features（s）?for?s?in?sentences]
????????self.model.fit（features?tag_lists）
????def?test（self?sentences）:
????????features?=?[self.sent2features（s）?for?s?in?sentences]
????????pred_tag_lists?=?self.model.pred ?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2019-06-29?09:00??crf_chinese_ner\
?????文件????????1584??2019-06-29?07:36??crf_chinese_ner\crf.py
?????文件????????2799??2019-06-29?08:41??crf_chinese_ner\main.py
?????文件??????????79??2019-06-29?08:51??crf_chinese_ner\requirement.txt
?????文件???????13713??2019-06-29?08:58??crf_chinese_ner\output.txt
?????文件????????6449??2019-06-29?08:57??crf_chinese_ner\evaluating.py
?????文件????????1002??2019-06-29?09:00??crf_chinese_ner\README.md
?????文件??????????31??2019-04-09?13:35??crf_chinese_ner\.gitignore
?????目錄???????????0??2019-06-29?08:40??crf_chinese_ner\model\
?????文件??????991931??2019-06-29?08:58??crf_chinese_ner\model\crf.pkl
?????目錄???????????0??2019-06-29?08:49??crf_chinese_ner\data\
?????文件?????1094528??2019-06-29?08:49??crf_chinese_ner\data\train.char.txt
?????文件??????135064??2019-06-29?08:49??crf_chinese_ner\data\test.char.txt
?????文件??????120251??2019-06-29?08:49??crf_chinese_ner\data\dev.char.txt
?????目錄???????????0??2019-06-29?08:57??crf_chinese_ner\__pycache__\
?????文件????????5677??2019-06-29?08:57??crf_chinese_ner\__pycache__\evaluating.cpython-35.pyc
?????文件????????2145??2019-06-29?08:57??crf_chinese_ner\__pycache__\crf.cpython-35.pyc
評論
共有 條評論