Aspect-level sentiment classification aims at identifying the sentiment polarity of specific target in its context. Previous approaches have realized the importance of targets in sentiment classification and developed various methods with the goal of precisely modeling their contexts via generating target-specific representations. However, these studies always ignore the separate modeling of targets. In this paper, we argue that both targets and contexts deserve special treatment and need to be learned their own representations via interactive learning. Then, we propose the interactive attention networks (IAN) to interactively learn attentions in the contexts and targets, and generate the representations for targets and contexts separately. With this design, the IAN model can well represent a target and its collocative context, which is helpful to sentiment classification. Experimental results on SemEval 2014 Datasets demonstrate the effectiveness of our model.

Recently, researches have explored the graph neural network (GNN) techniques on text classification, since GNN does well in handling complex structures and preserving global information. However, previous methods based on GNN are mainly faced with the practical problems of fixed corpus level graph structure which do not support online testing and high memory consumption. To tackle the problems, we propose a new GNN based model that builds graphs for each input text with global parameters sharing instead of a single graph for the whole corpus. This method removes the burden of dependence between an individual text and entire corpus which support online testing, but still preserve global information. Besides, we build graphs by much smaller windows in the text, which not only extract more local features but also significantly reduce the edge numbers as well as memory consumption. Experiments show that our model outperforms existing models on several text classification datasets even with consuming less memory.

In recent decades, the impact of dengue has increased both geographically and in intensity, and this disease is now a threat to approximately half of the world's population. An unexpected large outbreak of dengue fever was reported in Xishuangbanna Dai Autonomous Prefecture, Yunnan Province, China, in 2013. This was the first autochthonous outbreak with a significant proportion of severe dengue cases in mainland China in a decade. According to the 2009 World Health Organization guidelines, half of the 136 laboratory confirmed cases during the epidemic were severe dengue. The clinical presentation included severe haemorrhage (such as massive vaginal and gastrointestinal bleeding), severe plasma leakage (such as pleural effusion, ascites, or hypoproteinaemia), and organ involvement (such as myocarditis and lung impairment); 21 cases eventually deteriorated to shock. During this outbreak, all severe cases occurred in adults, among whom about 43% had co-morbid conditions. Nucleic acid detection and virus isolation confirmed dengue virus serotype 3 (DENV-3) to be the pathogenic agent of this outbreak. Phylogenetic analyses of envelope gene sequences showed that these DENV-3 isolates belonged to genotype II. This finding is of great importance to understand the circulation of DENV and predict the risk of severe disease in mainland China. Here, we provide a brief report of the epidemiology, clinical manifestations, and aetiology of this dengue fever outbreak, and characterize DENV strains isolated from clinical specimens.

Aspect term extraction (ATE) aims at identifying all aspect terms in a sentence and is usually modeled as a sequence labeling problem. However, sequence labeling based methods cannot make full use of the overall meaning of the whole sentence and have the limitation in processing dependencies between labels. To tackle these problems, we first explore to formalize ATE as a sequence-tosequence (Seq2Seq) learning task where the source sequence and target sequence are composed of words and labels respectively. At the same time, to make Seq2Seq learning suit to ATE where labels correspond to words one by one, we design the gated unit networks to incorporate corresponding word representation into the decoder, and position-aware attention to pay more attention to the adjacent words of a target word. The experimental results on two datasets show that Seq2Seq learning is effective in ATE accompanied with our proposed gated unit networks and position-aware attention mechanism.