Fix deadlines (PaddlePaddle#491)

* fix deadlinks

* fix deadlinks

README.md

@@ -151,7 +151,7 @@ PaddleNLP基于PaddlePaddle 2.0全新API体系，提供了丰富的应用场景
 | :--------------- | ---------- |
 | [SimNet](./examples/text_matching/simnet/)  | 百度提出的的语义匹配框架，主要使用BOW、CNN、GRNN等核心网络作为表示层，适用于信息检索、新闻推荐、智能客服等多种语义匹配应用场景。|
 | [ERNIE](./examples/text_matching/ernie_matching/) | 基于ERNIE使用LCQMC数据完成中文句对匹配任务，提供了Pointwise和Pairwise两种类型学习方式。 |
-| [Sentence-BERT](./examples/text_matching/sentence_transformer/) | 基于Siamese双塔结构的[Sentence-BERT](https://arxiv.org/abs/1908.1008)文本匹配模型，可用于获取基于Transformer预训练模型的句子向量化表示。
+| [Sentence-BERT](./examples/text_matching/sentence_transformers/) | 基于Siamese双塔结构的[Sentence-BERT](https://arxiv.org/abs/1908.1008)文本匹配模型，可用于获取基于Transformer预训练模型的句子向量化表示。
 
 #### 语义索引 (Semantic Indexing)
 

README_en.md

@@ -90,7 +90,7 @@ electra = ElectraModel.from_pretrained('chinese-electra-small')
 gpt = GPTForPretraining.from_pretrained('gpt-cpm-large-cn')
 ```
 
-For more pretrained model selection, please refer to [Transformer API](./docs/transformers.md)
+For more pretrained model selection, please refer to [Transformer API](./docs/model_zoo/transformers.rst)
 
 ### Extract Feature Through Pre-trained Model
 
@@ -128,7 +128,7 @@ For model zoo introduction please refer to[PaddleNLP Model Zoo](./docs/model_zoo
 
 ## API Usage
 
-- [Transformer API](./docs/transformers.md)
+- [Transformer API](./docs/model_zoo/transformers.rst)
 - [Data API](./docs/data.md)
 - [Dataset API](./docs/datasets.md)
 - [Embedding API](./docs/embeddings.md)

docs/model_zoo.md

@@ -25,7 +25,6 @@ PaddleNLP提供了丰富的模型结构，包含经典的RNN类模型结构，
 | ------ | ------ |
 | [Transformer](../examples/machine_translation/transformer/) | [Attention Is All You Need](https://arxiv.org/abs/1706.03762)     |
 | [Transformer-XL](../examples/language_model/transformer-xl/) | [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://arxiv.org/abs/1901.02860)     |
-| [ALBERT](../examples/language_model/albert/) | [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942)      |
 | [BERT](../examples/language_model/bert/) | [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805)      |
 | [ERNIE](../examples/text_classification/pretrained_models) | [ERNIE: Enhanced Representation through Knowledge Integration](https://arxiv.org/abs/1904.09223)   |
 | [ERNIE-Tiny](../examples/text_classification/pretrained_models) | 百度自研的小型化ERNIE网络结构，采用浅层Transformer，加宽隐层参数，中文subword粒度词表结合蒸馏的方法使模型相比SOTA Before BERT 提升8.35%， 速度提升4.3倍。 |