Convolutional multi-head self-attention on memory for aspect sentiment classification

This paper presents a method for aspect based sentiment classification tasks, named convolutional multi-head self-attention memory network &#x0028 CMA-MemNet &#x0029 . This is an improved model based on memory networks, and makes it possible to extract more rich and complex semantic information from sequences and aspects. In order to fix the memory network&#x02BC s inability to capture context-related information on a word-level, we propose utilizing convolution to capture n-gram grammatical information. We use multi-head self-attention to make up for the problem where the memory network ignores the semantic information of the sequence itself. Meanwhile, unlike most recurrent neural network &#x0028 RNN &#x0029 long short term memory &#x0028 LSTM &#x0029 , gated recurrent unit &#x0028 GRU &#x0029 models, we retain the parallelism of the network. We experiment on the open datasets SemEval-2014 Task 4 and SemEval-2016 Task 6. Compared with some popular baseline methods, our model performs excellently.