Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
DeepIE: Deep Learning for Information Extraction
| Date | Stars |
|---|---|
| 2026-08-02 | 1937 |
| 2026-08-06 | 1937 |
| 2026-08-08 | 1936 |
| 2026-08-12 | 1936 |
| 2026-08-13 | 1935 |
| 2026-08-15 | 1932 |
| 2026-08-18 | 1932 |
| 2026-08-22 | 1931 |
| 2026-08-24 | 1932 |
| 2026-09-03 | 1931 |
| 2026-09-30 | 1930 |
| 2026-10-10 | 1929 |
| 2026-10-19 | 1928 |
| 2026-10-31 | 1929 |
| 2026-11-04 | 1929 |
Today
— stars today
This week
+1 stars this week
This month
-1 stars this month
Momentum
0.0
growth rate 0.05%/day
# DeepIE: Deep Learning for Information Extraction **DeepIE**： 基于深度学习的信息抽取技术（预计2020年8月31日前全部更新完毕） ## TOP - **知乎专栏文章**：[nlp中的实体关系抽取方法总结](https://github.com/loujie0822/DeepIE/blob/jielou/docs/实体关系抽取算法总结.md) - **知乎专栏文章**：[如何有效提升中文NER性能？词汇增强方法总结](https://zhuanlan.zhihu.com/p/142615620) - **知乎专栏文章**：[如何解决Transformer在NER任务中效果不佳的问题？](https://zhuanlan.zhihu.com/p/137315695) ## Papers - [ACL2020信息抽取相关论文汇总](https://github.com/loujie0822/DeepIE/blob/master/docs/ACL2020信息抽取相关论文汇总.md) - [IJCAI2020信息抽取相关论文汇总](https://github.com/loujie0822/DeepIE/blob/master/docs/IJCAI2020_%E4%BF%A1%E6%81%AF%E6%8A%BD%E5%8F%96%E7%9B%B8%E5%85%B3%E8%AE%BA%E6%96%87%E5%90%88%E9%9B%86%20.md) - [2019各顶会中的关系抽取论文汇总](https://github.com/loujie0822/DeepIE/blob/master/docs/2019各顶会中的关系抽取论文]汇总.md) - [事件抽取论文汇总](https://github.com/loujie0822/DeepIE/blob/master/docs/事件抽取论文汇总.md) - [历年来NER论文汇总](https://github.com/loujie0822/DeepIE/blob/master/docs/历年来NER论文汇总.md) ## Codes #### 1. 实体抽取 - **各主流方法在主要中文NER数据集上的表现情况** [具体说明](https://github.com/loujie0822/DeepIE/blob/master/docs/各主流方法在中文NER上的表现情况.md) | | **lexicon** | **Ontonotes** | **MSRA** | **Resume** | **Weibo** | | -------------- | ----------- | ------------- | --------- | ---------- | --------- | | biLSTM | ---- | 71.81 | 91.87 | 94.41 | 56.75 | | Lattice LSTM | 词表1 | 73.88 | 93.18 | 94.46 | 58.79 | | WC-LSTM | 词表1 | 74.43 | 93.36 | 94.96 | 49.86 | | LR-CNN | 词表1 | 74.45 | 93.71 | 95.11 | 59.92 | | CGN | 词表2 | 74.79 | 93.47 | 94.12 | 63.09 | | LGN | 词表1 | 74.85 | 93.63 | 95.41 | 60.15 | | Simple-Lexicon | 词表1 | 75.54 | 93.50 | **95.59** | 61.24 | | FLAT | 词表1 | **76.45** | 94.12 | 95.45 | 60.32 | | FLAT | 词表2 | 75.70 | **94.35** | 94.93 | **63.42** | | BERT | ---- | 80.14 | 94.95 | 95.53 | 68.20 | | BERT+FLAT | 词表1 | **81.82** | **96.09** | **95.86** | **68.55** | - **MSRA-NER** | 方法 | f | p | r | | -------------------------------------------- | ---------- | ---------- | ---------- | | char+ lstm-crf | 86.18% | 88.43% | 83.10% | | char-bigram + lstm-crf | 91.80% | 92.60% | 90.34% | | char-bigram + adTransformer-crf | 92.98% | 93.25% | 92.72% | | char-bigram + lexion-augment + lstm-crf | 93.33% | 94.26% | 92.43% | | char-bigram-BERT + lstm-crf | 94.71% | 95.14% | 94.27% | | char-bigram-BERT + lexion-augment + lstm-crf | **95.26%** | **95.90%** | **94.63%** | - **CCKS2019-医疗实体抽取** | 方法 | f | p | r | | -------------------------------------------- | ---------- | ---------- | ---------- | | char-bigram + lstm-crf | 81.76% | 82.91% | 80.6 | | + domain transfer（from ccks2018 to 2019） | 82.54% | 83.43% | 81.81% | | char-bigram + adTransformer-crf | 82.83% | 82.19% | 83.49% | | char-bigram + lexion-augment + lstm-crf | 82.76% | 82.79% | 82.72% | | BERT-finetune+crf | 83.49% | 84.11% | 82.89% | | roBERTa-finetune+crf | 83.66% | 83.67% | 83.66% | | char-bigram-BERT + lstm-crf | 83.37% | 83.51% | 83.22% | | char-bigram-BERT + lexion-augment + lstm-crf | **84.15%** | **84.29%** | **84.01%** | - **CCKS2020-医疗实体抽取**： (注：测试集与ccks2019一致，去除ccks2020训练集中已经在2019测试集中的样本，下列指标未做规则处理和模型融合) | 方法 | f | p | r | | ------------------------------------------
Excerpt of 6,489 characters
Read on GitHub
259
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f84d345794f08f32, desc:information extraction