update reproduction/README.md

reproduction/README.md

@@ -2,43 +2,28 @@
 这里复现了在fastNLP中实现的模型，旨在达到与论文中相符的性能。
 
 复现的模型有:
-- Star-Transformer
+- [Star-Transformer](Star-transformer/)
 - ...
 
-
-## Star-Transformer
-[reference](https://arxiv.org/abs/1902.09113)
-### Performance (still in progress)
-|任务| 数据集 | SOTA | 模型表现 |
-|------|------| ------| ------|
-|Pos Tagging|CTB 9.0|-|ACC 92.31|
-|Pos Tagging|CONLL 2012|-|ACC 96.51|
-|Named Entity Recognition|CONLL 2012|-|F1 85.66|
-|Text Classification|SST|-|49.18|
-|Natural Language Inference|SNLI|-|83.76|
-
-### Usage
-``` python
-# for sequence labeling(ner, pos tagging, etc)
-from fastNLP.models.star_transformer import STSeqLabel
-model = STSeqLabel(
-    vocab_size=10000, num_cls=50,
-    emb_dim=300)
+# 任务复现
+## Text Classification (文本分类)
+- still in progress
 
 
-# for sequence classification
-from fastNLP.models.star_transformer import STSeqCls
-model = STSeqCls(
-    vocab_size=10000, num_cls=50,
-    emb_dim=300)
+## Matching (自然语言推理/句子匹配)
+- still in progress
 
 
-# for natural language inference
-from fastNLP.models.star_transformer import STNLICls
-model = STNLICls(
-    vocab_size=10000, num_cls=50,
-    emb_dim=300)
+## Sequence Labeling (序列标注)
+- still in progress
+
+
+## Coreference resolution (指代消解)
+- still in progress
+
+
+## Summarization (摘要)
+- still in progress
 
-```
 
 ## ...

reproduction/Star_transformer/README.md

@@ -0,0 +1,34 @@
+# Star-Transformer
+paper: [Star-Transformer](https://arxiv.org/abs/1902.09113)
+## Performance (still in progress)
+|任务| 数据集 | SOTA | 模型表现 |
+|------|------| ------| ------|
+|Pos Tagging|CTB 9.0|-|ACC 92.31|
+|Pos Tagging|CONLL 2012|-|ACC 96.51|
+|Named Entity Recognition|CONLL 2012|-|F1 85.66|
+|Text Classification|SST|-|49.18|
+|Natural Language Inference|SNLI|-|83.76|
+
+## Usage
+``` python
+# for sequence labeling(ner, pos tagging, etc)
+from fastNLP.models.star_transformer import STSeqLabel
+model = STSeqLabel(
+    vocab_size=10000, num_cls=50,
+    emb_dim=300)
+
+
+# for sequence classification
+from fastNLP.models.star_transformer import STSeqCls
+model = STSeqCls(
+    vocab_size=10000, num_cls=50,
+    emb_dim=300)
+
+
+# for natural language inference
+from fastNLP.models.star_transformer import STNLICls
+model = STNLICls(
+    vocab_size=10000, num_cls=50,
+    emb_dim=300)
+
+```

reproduction/matching/test/test_snlidataloader.py

@@ -1,6 +1,6 @@
 import unittest
-from reproduction.matching.data import SNLIDataLoader
-from fastNLP.core.vocabulary import VocabularyOption
+from ..data import SNLIDataLoader
+from fastNLP.core.vocabulary import Vocabulary
 
 
 class TestCWSDataLoader(unittest.TestCase):

reproduction/seqence_labelling/cws/test/test_CWSDataLoader.py

@@ -1,7 +1,7 @@
 
 
 import unittest
-from reproduction.seqence_labelling.cws.data.CWSDataLoader import SigHanLoader
+from ..data.CWSDataLoader import SigHanLoader
 from fastNLP.core.vocabulary import VocabularyOption