Abstract
Aspect-level sentiment analysis is a fundamental task in NLP, and it aims to predict the sentiment polarity of each specific aspect term in a given sentence. Recent researches show that the fine-grained sentiment analysis for aspect-level has become a research hotspot. However, previous work did not consider the influence of grammatical rules on aspect-level sentiment analysis. In addition, attention mechanism is too simple to learn attention information from context and target interactively. Therefore, we propose an interactive rule attention network (IRAN) for aspect-level sentiment analysis. IRAN not only designs a grammar rule encoder, which simulates the grammatical functions at the sentence by standardizing the output of adjacent positions, but also constructs an interaction attention network to learn attention information from context and target. Experimental results on SemEval 2014 Dataset and ACL 2014 Twitter Dataset demonstrate IRAN can learn effective features and obtain superior performance over the baseline models.
Highlights
Sentiment analysis, known as opinion mining [1], [2], is one of the fundamental tasks of natural language processing [3], [4], and it aims to predict the sentiment polarities of the given texts
Our main contributions can be summarized as follows: 1) We propose an interactive rule attention network (IRAN) for aspect-level sentiment analysis, which has been proved to be effective to improve the sentiment analysis performance
The results of our model and baseline models on datasets Restaurant, Laptop and Twitter are shown in Table 2, we find that IRAN has better performance than most frontier models on Accuracy and F1-Measure, which verifies the effectiveness of our model
Summary
Known as opinion mining [1], [2], is one of the fundamental tasks of natural language processing [3], [4], and it aims to predict the sentiment polarities of the given texts. Sentiment analysis models for aspect-level have recently been introduced attention mechanism to models and achieved great results [17]–[20]. In order to address the above problems, we propose an interactive rule attention network (IRAN) for aspect-level sentiment analysis. Compared with the traditional aspect-level sentiment analysis models, our model introduces the external knowledge of grammar rules to the model so that can learn more grammar information from hidden states. We design an interactive attention mechanism which adopts multi-attention mechanism to learn the mutual information between context and aspect interactively. Our main contributions can be summarized as follows: 1) We propose an interactive rule attention network (IRAN) for aspect-level sentiment analysis, which has been proved to be effective to improve the sentiment analysis performance.
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.
