Aspect sentiment classification, a challenging task in sentiment analysis, has been attracting more and more attention in recent years. In this paper, we highlight the need for incorporating the importance degrees of both words and clauses inside a sentence and propose a hierarchical network with both word-level and clause-level attentions to aspect sentiment classification. Specifically, we first adopt sentence-level discourse segmentation to segment a sentence into several clauses. Then, we leverage multiple Bi-directional LSTM layers to encode all clauses and propose a word-level attention layer to capture the importance degrees of words in each clause. Third and finally, we leverage another Bi-directional LSTM layer to encode the outputs from the former layers and propose a clause-level attention layer to capture the importance degrees of all the clauses inside a sentence. Experimental results on the laptop and restaurant datasets from SemEval-2015 demonstrate the effectiveness of our proposed approach to aspect sentiment classification.
Ferroelastics, as an important member of ferroic materials, play an invaluable role in energy conversion, information processing, and mechanical switches. However, to date, it remains an arduous task to construct molecular ferroelastics with dielectric bistability/switching characteristics. Within this context, moreover, controlling the multiswitching behavior in dielectrics has been a great challenge, while imparting them with other fascinating properties (ferroelasticity and semiconducting features) is even more laborious. Here, through a molecular modification strategy, we successfully designed an organic−inorganic hybrid ferroelastic with a band gap of 2.58 eV, (DMTBA) 3 Bi 2 Br 9 (DMTBA = N,Ndimethyl-tert-butylaminium), which exhibits dual-dielectric switching characteristics at 425 and 188 K. These attributes make it a multifunctional material for multipurpose sensors, mechanical switches, and photoelectric devices. Compared to other methylsubstituted products, (N,N-dimethyl-tert-butylaminium) 3 Bi 2 Br 9 and (N,N,N-trimethyl-tert-butylaminium) 3 Bi 2 Br 9 , proper molecular interactions and dynamics of DMTBA cations should be responsible for its ferroelasticity with dual dielectric switches. We expect that this study would throw light on the rational design of new hybrid ferroelastics with multifunctional characteristics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.