Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification阅读笔记
Att-BLSTM
Model
<center>
</center> 模型主要包括五部分:
- Input layer
- Embedding layer
- Lstm layer
- Attention layer
- Output layer
Word Embedding
没啥好说的…
Bidirectional Network
Bi-LSTM结构, 最后输出
<center>
</center> Attention
Attention部分, 先对LSTM输出做非线性激活, 然后计算attention权重.
<center>
</center> 最终的句表示:
<center>
</center> Classifying
<center>
</center> 损失函数: 加上L2正则的交叉熵
<center>
</center> 实验
数据集: SemEval-2010
参数设置:
word embedding: 分别尝试了50, 100
optimizer: AdaDelta
learning rate: 1.0
batch size: 10
dropout: 0.3, 0.3, 0.5
评价指标: macro-F1score
</center>