add suggested readings

huige555551 · Jul 10, 2017 · 8cef8a3 · 8cef8a3
1 parent 8ba9de4
commit 8cef8a3
Showing 1 changed file with 3 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -45,15 +45,15 @@ Propose a unified neural network architecture for sequence labeling tasks.
 2. [Neural Architectures for Named Entity Recognition](http://arxiv.org/abs/1603.01360).  
 [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF](http://www.cs.cmu.edu/~xuezhem/publications/lstm-cnn-crf.pdf).  
 Combine Character-based word representations and word representations to enhance sequence labeling systems.
-3. [TRANSFER LEARNING FOR SEQUENCE TAGGING WITH HIERARCHICAL RECURRENT NETWORKS](http://www.cs.cmu.edu/~./wcohen/postscript/iclr-2017-transfer.pdf).  
+3. [Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks](http://www.cs.cmu.edu/~./wcohen/postscript/iclr-2017-transfer.pdf).  
 [Multi-task Multi-domain Representation Learning for Sequence Tagging](http://xueshu.baidu.com/s?wd=paperuri%3A%288d2ae013d4ea38b3aba07a5f5cf8c8d1%29&filter=sc_long_sign&tn=SE_xueshusource_2kduw22v&sc_vurl=http%3A%2F%2Farxiv.org%2Fpdf%2F1608.02689v1.pdf&ie=utf-8&sc_us=16810667041741374202).  
 Transfer learning for sequence tagging.
 4. [Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings](http://www.aclweb.org/website/anthology/D/D15/D15-1064.pdf).  
 Propose a joint training objective for the embeddings that makes use of both (NER) labeled and unlabeled raw text
-5. [Improving named entity recognition for chinese social media with word segmentation representation learning](http://anthology.aclweb.org/P/P16/P16-2025.pdf).  
+5. [Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning](http://anthology.aclweb.org/P/P16/P16-2025.pdf).  
 [An Empirical Study of Automatic Chinese Word Segentation for Spoken Language Understanding and Named Entity Recognition](http://www.aclweb.org/anthology/N/N16/N16-1028.pdf).  
 Using word segmentation outputs as additional features for sequence labeling syatems.
-6. [Semi-supervised sequence tagging with bidirectional language models](http://xueshu.baidu.com/s?wd=paperuri%3A%28e7dcf1a507dabc77f1e26c28068ca937%29&filter=sc_long_sign&tn=SE_xueshusource_2kduw22v&sc_vurl=http%3A%2F%2Farxiv.org%2Fpdf%2F1705.0108&ie=utf-8&sc_us=17831018953161676191).  
+6. [Semi-supervised Sequence Tagging with Bidirectional Language Models](http://xueshu.baidu.com/s?wd=paperuri%3A%28e7dcf1a507dabc77f1e26c28068ca937%29&filter=sc_long_sign&tn=SE_xueshusource_2kduw22v&sc_vurl=http%3A%2F%2Farxiv.org%2Fpdf%2F1705.0108&ie=utf-8&sc_us=17831018953161676191).  
 State-of-the-art model on Conll03 NER task, adding pre-trained context embeddings from bidirectional language models for sequence labeling task.
 7. [Character-Based LSTM-CRF with Radical-Level Features for Chinese Named Entity Recognition](http://tcci.ccf.org.cn/conference/2016/papers/119.pdf).  
 State-of-the-art model on SIGHAN2006 NER task.