Aspect term extraction is one of the important subtasks in aspect-based sentiment analysis. Previous studies have shown that using dependency tree structure representation is promising for this task. However, most dependency tree structures involve only one directional propagation on the dependency tree. In this paper, we first propose a novel bidirectional dependency tree network to extract dependency structure features from the given sentences. The key idea is to explicitly incorporate both representations gained separately from the bottom-up and top-down propagation on the given dependency syntactic tree. An end-to-end framework is then developed to integrate the embedded representations and BiLSTM plus CRF to learn both tree-structured and sequential features to solve the aspect term extraction problem. Experimental results demonstrate that the proposed model outperforms state-of-the-art baseline models on four benchmark SemEval datasets. ↑( * ) r ↑ (k) , U ↑( * ) r ↑ (k) are weight matrices, b ↑( * ) are bias vectors,
The World-PEde Web consists not only of informational, but also computational resources. However: these resources, especially computational ones are underutilized. One characteristic of the Web is its ever changingstructure; for instance, nodes are dynamically added and removed. This makes it dificult, ifnot impossible, to draw a complete and accurate picture of available resources. We consider the Web as a versioned system: resources, services andprotocols are versioned. This paper presents a two-level protocol within this framework. The ,first protocol, the WOS Request Protocol (WOSRP), allows to select an appropriate version of a sewer: The secondprotocol, the WOS Protocol (WOSP), allows for locating and using these distributed (in-,formational and computational) resources. We show how the latter protocol provides an eficient ,fault-tolerant resource search mechanism.
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.