You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
V^s的部分是一个map 函数,把一个word set变成fixed-dimensional vector。这里引入了mean-pooling算法来表示word set S的vector representation:
但是mean-pooling的效果并不好。Lattice-LSTM里使用了dynamical weighting algorithm,为了保证速度,这里才用的weighting 方法是 the frequency of the word as an indication of its weight. The basic idea beneath this algorithm is that the more times a character sequence occurs in the data, the more likely it is a word. Note that, the frequency of a word is a static value and can be obtained offline. This can greatly accelerate the calculation of the weight of each word (e.g., using a lookup table).
这里还专门提高infrequent words的权重
Model Graph:
Result::
Thoughts:
Next Reading:
The text was updated successfully, but these errors were encountered:
Summary:
因为 Lattice-LSTM #279 运算效率太低。所以这篇文章希望更有效地把lexicon information导入到character representation里。
Resource:
Paper information:
Notes:
作者分析了 Lattice-LSTM的优缺点。
优点:
所以这篇文章的想法是在保持上面优点的情况下,舍弃原来的LSTM模型。作者提出的方法是提出了一种新的编码方式。
一个句子s中的每一个字符c,都有对应的4个word sets。这个word sets是通过“BMES”4个标签来标记的。
如果集合为空则成员为None。
Consider the sentence s = {c1, · · · , c5} and suppose that {c1, c2}, {c1, c2, c3}, {c2, c3, c4}, and {c2, c3, c4, c5} match the lexicon. Then, for c2, B(c2) = {{c2, c3, c4}, {c2, c3, c4, c5}}, M(c2) = {{c1, c2, c3}}, E(c2) = {{c1, c2}}, and S(c2) = {NONE}.
这里例子里的B(c2) = {{c2, c3, c4}, {c2, c3, c4, c5}},B(“南”)= {南京市,南京大桥}。
V^s的部分是一个map 函数,把一个word set变成fixed-dimensional vector。这里引入了mean-pooling算法来表示word set S的vector representation:
但是mean-pooling的效果并不好。Lattice-LSTM里使用了dynamical weighting algorithm,为了保证速度,这里才用的weighting 方法是 the frequency of the word as an indication of its weight. The basic idea beneath this algorithm is that the more times a character sequence occurs in the data, the more likely it is a word. Note that, the frequency of a word is a static value and can be obtained offline. This can greatly accelerate the calculation of the weight of each word (e.g., using a lookup table).
这里还专门提高infrequent words的权重
Model Graph:
Result::
Thoughts:
Next Reading:
The text was updated successfully, but these errors were encountered: