Abstract
Aspect-based sentiment classification aims to detect the sentiment polarity of a target in a given context. Most previous approaches use long short-term memory (LSTM) and attention mechanisms to predict the sentiment polarity of targets, which are usually complex and need more training time. Some previous approaches are based on convolutional neural networks (CNN) and gating mechanisms, which are much simpler, efficient and takes lesser convergence time than LSTM due to parallelized computations during training. However, such CNN-based networks ignore the separate modeling of targets via context-specific representations. In this paper, we propose a novel interactive gated convolutional network (IGCN) that uses a bidirectional gating mechanism to learn mutual relation between the target and corresponding review context. IGCN also uses positional information of context words with respect to the given target, POS tags, and domain-specific word embeddings for predicting the sentiment of a target. The experimental results on SemEval 2014 datasets show the effectiveness of our proposed IGCN model.
Highlights
Sentiment analysis is an important task in Natural Language Processing (NLP), which analyzes the user’s review comment about a product or an event and provides the user’s sentiment about it
GCAE model is based on convolutional neural networks and gating mechanisms, GCAE uses Gated Tanh-ReLU Units that captures the sentiment features of the context according to the given target
long short-term memory (LSTM) performs the worst among all the methods as it does not distinguish the difference between target and other words used in the context
Summary
Sentiment analysis is an important task in Natural Language Processing (NLP), which analyzes the user’s review comment about a product or an event and provides the user’s sentiment about it. Xue and Li [6] present a gated mechanism-based convolution neural network that takes lesser time than attention-based LSTM network and provides better accuracy In this network, the gating mechanism plays a vital role in selectively extracting target-specific sentiment information from a review context for a given target. IGCN uses a bidirectional gating mechanism-based convolutional network to understand the mutual relation between the target and its corresponding review context and ignore the unnecessary words from getting undue importance. To capture the critical information of the context for a given target, Tang et al [2] build an attention-based model, which learns the importance or weight of each word of the context and subsequently, use this information in forming the context representation. Where W1a ∈ Rq×d and bt ∈ R are convolution filter and bias respectively
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
