基于多注意力卷积神经网络的特定目标情感分析

特定目标情感分析作为情感分析一个重要的子任务，近年来得到越来越多研究人员的关注.针对在特定目标情感分析中，将注意力机制和LSTM等序列性输入网络相结合的网络模型训练时间长、且无法对文本进行平行化输入等问题，提出一种基于多注意力卷积神经网络(multi-attention convolution neural networks, MATT-CNN)的特定目标情感分析方法.相比基于注意力机制的LSTM网络，该方法可以接收平行化输入的文本信息，大大降低了网络模型的训练时间.同时，该方法通过结合多种注意力机制有效弥补了仅仅依赖内容层面注意力机制的不足，使模型在不需要例如依存句法分析等外部知识的情况下，获取更深层次的情感特征信息，有效识别不同目标的情感极性.最后在SemEval2014数据集和汽车领域数据集(automotive-domain data, ADD)进行实验，取得了比普通卷积神经网络、基于单注意力机制的卷积神经网络和基于注意力机制的LSTM网络更好的效果.

Aspect-Based Sentiment Analysis Based on Multi-Attention CNN

Unlike general sentiment analysis, aspect-based sentiment classification aims to infer the sentiment polarity of a sentence depending not only on the context but also on the aspect. For example, in sentence “The food was very good, but the service at that restaurant was dreadful”, for aspect “food”, the sentiment polarity is positive while the sentiment polarity of aspect “service” is negative. Even in the same sentence, sentiment polarity could be absolutely opposite when focusing on different aspects, so we need to infer the sentiment polarities of different aspects correctly. The attention mechanism is a good way for aspect-based sentiment classification. In current research, however, the attention mechanism is more combined with RNN or LSTM networks. Such neural network-based architectures generally rely on complex structures and cannot parallelize over the words of a sentence. To address the above problems, this paper proposes a multi-attention convolutional neural networks (MATT-CNN) for aspect-based sentiment classification. This approach can capture deeper level sentiment information and distinguish sentiment polarity of different aspects explicitly through a multi-attention mechanism without using any external parsing results. Experiments on the SemEval2014 and Automotive-domain datasets show that, our approach achieves better performance than traditional CNN, attention-based CNN and attention-based LSTM.