About make_batch of NNLM

```python
input = [word_dict[n] for n in word[:-1]] # create (1~n-1) as input
target = [word_dict[word[-1]]]
```

it constraints the length of input and n_step. I think the following example is even better

```python
for i in range(len(words) - window_size + 1):`
` x_train.append(words[i: i + window_size - 1])`
`y_train.append(words[i + window_size - 1])
```

首先在 NNLM 教程中找到 make_batch 入口点，并阅读当前如何使用 input、target、word、n_step 和 window_size。将其生成的训练对与提议的滑动窗口示例进行比较；当批处理行为支持预期的窗口长度，且不限制 input 和 n_step 时，即视为完成。

由索引模型根据 Issue 内容生成。