基于多注意力长短时记忆的实体属性情感分析

属性情感分析是细粒度的情感分类任务。针对传统神经网络模型无法准确构建属性情感特征的问题,提出了一种融合多注意力和属性上下文的长短时记忆(LSTM-MATT-AC)神经网络模型。在双向长短时记忆(LSTM)的不同位置加入不同类型的注意力机制,充分利用多注意力机制的优势,让模型能够从不同的角度关注句子中特定属性的情感信息,弥补了单一注意力机制的不足;同时,融合双向LSTM独立编码的属性上下文语义信息,获取更深层次的情感特征,有效识别特定属性的情感极性;最后在Sem Eval2014 Task4和Twitter数据集上进行实验,验证了不同注意力机制和独立上下文处理方式对属性情感分析模型的有效性。实验结果表明,模型在Restaurant、Laptop和Twitter领域数据集上的准确率分别达到了80. 6%、75. 1%和71. 1%,较之前基于神经网络的情感分析模型在准确率上有了进一步的提高。

Sentiment analysis of entity aspects based on multi-attention long short-term memory

Aspect sentiment analysis is a fine-grained task in sentiment classification. Concerning the problem that traditional neural network model can not accurately construct sentiment features of aspects, a Long Short-Term Memory with Multi-ATTention and Aspect Context (LSTM-MATT-AC) neural network model was proposed. Different types of attention mechanisms were added in different positions of bidirectional Long Short-Term Memory (LSTM), and the advantage of multi-attention mechanism was fully utilized to allow the model to focus on sentiment information of specific aspects in sentence from different perspectives, which could compensate the deficiency of single attention mechanism. At the same time, combining aspect context information of bidirectional LSTM independent coding, the model could capture deeper level sentiment information and effectively distinguish sentiment polarity of different aspects. Experiments on SemEval2014 Task4 and Twitter datasets were carried out to verify the effectiveness of different attention mechanisms and independent context processing on aspect sentiment analysis. The experimental results show that the accuracy of the proposed model reaches 80.6%, 75.1% and 71.1% respectively for datasets in domain Restaurant, Laptop and Twitter. Compared with previous neural network-based sentiment analysis models, the accuracy has been further improved.