用于短文本情感分类的多头注意力记忆网络

随着社交网络的发展，对其包含的海量文本进行情感分析具有重要的社会价值。不同于普通文本分类，短文本情感分类需要挖掘隐含的情感语义特征，具有极大的难度和挑战性。为了能在更高的层次上得到短文本的情感语义特征，提出了一种多头注意力记忆网络（MAMN）用于短文本情感分类。首先，利用n元语法特征信息和有序神经元长短时记忆（ON-LSTM）网络对多头自注意力机制进行改进，以对文本上下文内联关系进行充分提取，使模型可以获得更丰富的文本特征信息。然后，利用多头注意力机制对多跳记忆网络的结构进行优化，使得在拓展模型深度的同时，挖掘更高层次的上下文内联情感语义关系。在电影评论集（MR）、斯坦福情感树（SST）-1和SST-2这三个不同的数据集上进行了大量实验。实验结果表明，与基于循环神经网络（RNN）和卷积神经网络（CNN）结构的基线模型以及一些最新成果相比，所提MAMN取得了较优的分类效果，验证了多跳结构对于性能改善的重要作用。

Multi-head attention memory network for short text sentiment classification

With the development of social networks， it has important social value to analyze the sentiments of massive texts in the social networks. Different from ordinary text classification， short text sentiment classification needs to mine the implicit sentiment semantic features， so it is very difficult and challenging. In order to obtain short text sentiment semantic features at a higher level， a new Multi-head Attention Memory Network （MAMN） was proposed for sentiment classification of short texts. Firstly， n-gram feature information and Ordered Neurons Long Short-Term Memory （ON-LSTM） network were used to improve the multi-head self-attention mechanism to fully extract the internal relationship of the text context， so that the model was able obtain richer text feature information. Secondly， multi-head attention mechanism was adopted to optimize the multi-hop memory network structure， so as to expand the depth of the model and mine higher level contextual internal semantic relations at the same time. A large number of experiments were carried out on Movie Review dataset （MR）， Stanford Sentiment Treebank （SST）-1 and SST-2 datasets. The experimental results show that compared with the baseline models based on Recurrent Neural Network （RNN） and Convolutional Neural Network （CNN） structure and some latest works， the proposed MAMN achieves the better classification results， and the importance of multi-hop structure in performance improvement is verified.