Abstract
Targeted sentiment classification aims to predict the emotional trend of a specific goal. Currently, most methods (e.g., recurrent neural networks and convolutional neural networks combined with an attention mechanism) are not able to fully capture the semantic information of the context and they also lack a mechanism to explain the relevant syntactical constraints and long-range word dependencies. Therefore, syntactically irrelevant context words may mistakenly be recognized as clues to predict the target sentiment. To tackle these problems, this paper considers that the semantic information, syntactic information, and their interaction information are very crucial to targeted sentiment analysis, and propose an attentional-encoding-based graph convolutional network (AEGCN) model. Our proposed model is mainly composed of multi-head attention and an improved graph convolutional network built over the dependency tree of a sentence. Pre-trained BERT is applied to this task, and new state-of-art performance is achieved. Experiments on five datasets show the effectiveness of the model proposed in this paper compared with a series of the latest models.
Highlights
Natural language processing is an important part of the new generation of artificial intelligence, in human–machine interaction [1]
Since the structure of the syntactic dependency tree is similar to the graph structure and the graph convolutional network (GCN) [17] is an effective convolutional neural network that is able to directly operate on graphs, this paper proposes an improved GCN to better extract and integrate the syntactic information displayed in the syntactic dependency tree of the sentences
For attentional-encoding-based graph convolutional network (AEGCN), a graph convolution network was deployed between the Bi-long short-term memory (LSTM) and multi-head self-attention in the proposed model, since it can reconstruct the representation of each word using syntactic information
Summary
Natural language processing is an important part of the new generation of artificial intelligence, in human–machine interaction [1]. Most of them are based on long short-term memory (LSTM) neural networks [8], and some of them are convolutional neural networks (CNNs) [9] Many of these neural-network-based methods embed specific target information into the sentence representation via an attention mechanism [7]. Another problem in previous research is that these methods largely ignore the syntactic structure of the sentence, while the syntactic structure helps to identify the emotional characteristics directly related to the specific target. Model, which leverages the syntactic structure of a sentence and utilizes multi-head self-attention combined with LSTM to capture context features and specific target features concurrently.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.