From 47008bb4d6da3688b6a8379b7b8cd1257f0c4b11 Mon Sep 17 00:00:00 2001
From: adolphk-yk <49522434+adolphk-yk@users.noreply.github.com>
Date: Sat, 22 Jun 2019 10:10:05 +0800
Subject: [PATCH] Modify sequence labeling  tutorial (#69)

* add sequence labeling in tutorial

* add tag scheme convert script

* add paper link

* modify sequence labeling tutorial

* modify senquence labeling tutorial
---
 Tutorial.md       | 28 +++++++++++++++++++++++++---
 Tutorial_zh_CN.md | 28 +++++++++++++++++++++++++---
 2 files changed, 50 insertions(+), 6 deletions(-)

diff --git a/Tutorial.md b/Tutorial.md
index fe8d95d..00a9cda 100644
--- a/Tutorial.md
+++ b/Tutorial.md
@@ -578,20 +578,42 @@ Sequence Labeling is an important NLP task, which includes NER, Slot Tagging, Po
 
 - ***Usages***
 
-    1. BiLSTM representation and Softmax output.
+    1. Softmax output.
     ```bash
+    # train model
     cd PROJECT_ROOT
     python train.py --conf_path=model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging.json
+    
+    # test model
+    cd PROJECT_ROOT
+    python test.py --conf_path=model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging.json
     ``` 
+    2. CRF output.
+    ```bash
+    # train model
+    cd PROJECT_ROOT
+    python train.py --conf_path=model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging_ccnn_wlstm_crf.json
+    
+    # test model
+    cd PROJECT_ROOT
+    python test.py --conf_path=model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging_ccnn_wlstm_crf.json
+    ```
+    *Tips: you can try more model in [here](https://github.com/microsoft/NeuronBlocks/tree/master/model_zoo/nlp_tasks/slot_tagging).*
     
 - ***Result***
     
-    1. BiLSTM representation and Softmax output.
+    The result on CoNLL 2003 English NER dataset.
     
     Model    | F1-score 
     -------- | -------- 
     [Ma and Hovy(2016)](https://arxiv.org/pdf/1603.01354.pdf)|87.00
-    BiLSTM+Softmax(NeuronBlocks)|88.50
+    [BiLSTM+Softmax](https://github.com/microsoft/NeuronBlocks/blob/master/model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging.json) (NeuronBlocks)|88.50
+    [Lample et al.(2016)](https://arxiv.org/pdf/1603.01360.pdf)| 89.15
+    [CLSTM+WLSTM+CRF](https://github.com/microsoft/NeuronBlocks/blob/master/model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging_clstm_wlstm_crf.json) (NeuronBlocks)|90.83
+    [Chiu and Nichols(2016)](https://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00104)|90.91
+    [CCNN+WLSTM+CRF](https://github.com/microsoft/NeuronBlocks/blob/master/model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging_ccnn_wlstm_crf.json) (NeuronBlocks)|91.38
+    
+    *Tips: C means Char and W means Word. CCNN means Char-level representation with CNN model and CLSTM means Char-level representation with LSTM model.*
     
 ## <span id="advanced-usage">Advanced Usage</span>
 
diff --git a/Tutorial_zh_CN.md b/Tutorial_zh_CN.md
index 53e6e60..dec8ca5 100644
--- a/Tutorial_zh_CN.md
+++ b/Tutorial_zh_CN.md
@@ -568,20 +568,42 @@ This task is to train a query-passage regression model to learn from a heavy tea
 
 - ***用法***
 
-    1. BiLSTM 词表示和 Softmax 输出
+    1. Softmax 输出.
     ```bash
+    # train model
     cd PROJECT_ROOT
     python train.py --conf_path=model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging.json
+    
+    # test model
+    cd PROJECT_ROOT
+    python test.py --conf_path=model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging.json
     ``` 
+    2. CRF 输出.
+    ```bash
+    # train model
+    cd PROJECT_ROOT
+    python train.py --conf_path=model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging_ccnn_wlstm_crf.json
+    
+    # test model
+    cd PROJECT_ROOT
+    python test.py --conf_path=model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging_ccnn_wlstm_crf.json
+    ```
+    *提示 ：尝试更多模型可 [点击](https://github.com/microsoft/NeuronBlocks/tree/master/model_zoo/nlp_tasks/slot_tagging)。*
     
 - ***结果***
 
-    1. BiLSTM 词表示和 Softmax 输出
+    实验采用 CoNLL 2003 英文 NER 数据集。
     
     Model    | F1-score 
     -------- | -------- 
     [Ma and Hovy(2016)](https://arxiv.org/pdf/1603.01354.pdf)|87.00
-    BiLSTM+Softmax(NeuronBlocks)|88.50
+    [BiLSTM+Softmax](https://github.com/microsoft/NeuronBlocks/blob/master/model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging.json) (NeuronBlocks)|88.50
+    [Lample et al.(2016)](https://arxiv.org/pdf/1603.01360.pdf)| 89.15
+    [CLSTM+WLSTM+CRF](https://github.com/microsoft/NeuronBlocks/blob/master/model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging_clstm_wlstm_crf.json) (NeuronBlocks)|90.83
+    [Chiu and Nichols(2016)](https://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00104)|90.91
+    [CCNN+WLSTM+CRF](https://github.com/microsoft/NeuronBlocks/blob/master/model_zoo/nlp_tasks/slot_tagging/conf_slot_tagging_ccnn_wlstm_crf.json) (NeuronBlocks)|91.38
+    
+    *提示 : C 代表字符，W 代表单词。 CCNN 代表使用 CNN 模型的字符级别表示， CLSTM 代表使用 LSTM 模型的字符级别表示。*
 
 ## <span id="advanced-usage">高阶用法</span>