fix multiview readme (PaddlePaddle#2766)

* fix word2vec Readme

* fix windows numpy int64 bug

* fix multiview Readme

Author: frankwhzhang

PaddleRec/multiview_simnet/README.cn.md

@@ -4,7 +4,7 @@
 在个性化推荐场景中，推荐系统给用户提供的项目（Item）列表通常是通过个性化的匹配模型计算出来的。在现实世界中，一个用户可能有很多个视角的特征，比如用户Id，年龄，项目的点击历史等。一个项目，举例来说，新闻资讯，也会有多种视角的特征比如新闻标题，新闻类别等。多视角Simnet模型是可以融合用户以及推荐项目的多个视角的特征并进行个性化匹配学习的一体化模型。这类模型在很多工业化的场景中都会被使用到，比如百度的Feed产品中。
 
 ## 数据集
-目前，本项目使用机器生成的数据集来介绍多视角Simnet模型的概念，未来我们会逐渐加入真实世界中的数据集并在这个模型上进行效果验证。
+目前，本项目使用机器生成的数据集来介绍多视角Simnet模型的概念，未来我们会逐渐加入真是世界中的数据集并在这个模型上进行效果验证。由于数据的原因，训练结果不准确。
 
 ## 模型
 本项目的目标是提供一个在个性化匹配场景下利用Paddle搭建的模型。多视角Simnet模型包括多个编码器模块，每个编码器被用在不同的特征视角上。当前，项目中提供Bag-of-Embedding编码器，Temporal-Convolutional编码器，和Gated-Recurrent-Unit编码器。我们会逐渐加入稀疏特征场景下比较实用的编码器到这个项目中。模型的训练方法，当前采用的是Pairwise ranking模式进行训练，即针对一对具有关联的User-Item组合，随机实用一个Item作为负例进行排序学习。
@@ -15,7 +15,7 @@
 ```bash
 python train.py
 ```
-## 
+##
 如下
 如下命令行可以获得预测工具的具体选项，`python infer -h`内容可以参考说明
 ```bash

PaddleRec/multiview_simnet/README.md

@@ -4,7 +4,8 @@
 In personalized recommendation scenario, a user often is provided with several items from personalized interest matching model. In real world application, a user may have multiple views of features, say user-id, age, click-history of items, search queries. A item, e.g. news, may also have multiple views of features like news title, news category, images in news and so on. Multi-view Simnet is matching a model that combine users' and items' multiple views of features into one unified model. The model can be used in many industrial product like Baidu's feed news. The model is adapted from the paper A Multi-View Deep Learning(MV-DNN) Approach for Cross Domain User Modeling in Recommendation Systems, WWW 2015. The difference between our model and the MV-DNN is that we also consider multiple feature views of users.
 
 ## Dataset
-Currently, synthetic dataset is provided for proof of concept and we aim to add more real world dataset in this project in the future.
+Currently, synthetic dataset is provided for proof of concept and we aim to add more real world dataset in this project in the future. The result is inaccurate because of synthetic dataset.
+
 
 ## Model
 This project aims to provide practical usage of Paddle in personalized matching scenario. The model provides several encoder modules for different views of features. Currently, Bag-of-Embedding encoder, Temporal-Convolutional encoder, Gated-Recurrent-Unit encoder are provided. We will add more practical encoder for sparse features commonly used in recommender systems. Training algorithms used in this model is pairwise ranking in that a negative item with multiple views will be sampled given a pair of positive user-item pair.