摘要

We report on a series of experiments with
convolutional neural networks (CNN)
trained on top of pre-trained word vectors for sentence-level classification tasks.
We show that a simple CNN with little hyperparameter tuning and static vectors achieves excellent results on multiple benchmarks. Learning task-specific
vectors through fine-tuning offers further
gains in performance. We additionally
propose a simple modification to the architecture to allow for the use of both
task-specific and static vectors. The CNN
models discussed herein improve upon the
state of the art on 4 out of 7 tasks, which
include sentiment analysis and question
classification

• 任务：句子级分类任务sentence-level classification tasks
• a simple CNN with little hyperparameter tuniing and static vectors.

模型架构

$$x_i\in R^k$$ the k-dimensional word vector
A sentence of length:$$n$$
$$x_{1:n}=x_1\otimes x_2\otimes \cdots ,\otimes x_n$$

$\otimes$is the concatenation operator.

$x_{i:i+j}$ 代表单词的拼接
$w\in R^{hk}$: 卷积滤波器。

卷积操作

a max-over-time pooling operation

$$\hat{c}=\max c$$

倒数第二层加入dropout ,防止过拟合。

解决了句子长度可变问题。

• the penultimate layer 倒数第二层

a fully connected softmax layer

数据集

MR

SST-1:

SST-2:

Subj

TREC

CR

• MPQA

更新算法

• 随机梯度下降法：Adadelta 算法
• 预训练词向量：the publicly available word2vec vectors

模型变体

• CNN-rand
• CNN-static
• CNN-non-static
• CNN-multichannel