The Recurrent Neural Network (RNN) utilizes dynamically changing time information through time cycles, so it is very suitable for tasks with time sequence characteristics. However, with the increase of the number of layers, the vanishing gradient occurs in the RNN. The Grid Long Short-Term Memory (GridLSTM) recurrent neural network can alleviate this problem in two dimensions by taking advantage of the two dimensions calculated in time and depth. In addition, the time sequence task is related to the information of the current moment before and after. In this paper, we propose a method that takes into account context-sensitivity and gradient problems, namely the Bidirectional Grid Long Short-Term Memory (BiGridLSTM) recurrent neural network. This model not only takes advantage of the grid architecture, but it also captures information around the current moment. A large number of experiments on the dataset LibriSpeech show that BiGridLSTM is superior to other deep LSTM models and unidirectional LSTM models, and, when compared with GridLSTM, it gets about 26 percent gain improvement.
Opportunistic network enables users to form an instant network for data sharing, which is a type of Ad-hoc network in nature, thus depends on cooperation between nodes to complete message transmission. Because of intermittent communication and frequent changes of topology structure in opportunistic networks, the duration of node encounters is limited, as well as the length of established connections. If the amount of interactive data is large and the communication bandwidth is small, the messages that need to be transmitted are not guaranteed to be delivered successfully every time. In this regard, this paper establishes a transmission prediction mechanism exploiting comprehensive node forwarding capability (TPMEC) in opportunistic networks. When quantifying the forwarding capability of nodes, the algorithm not only considers the cooperative tendency but also discusses the encounter strength between nodes. At the same time, in order to find out all key nodes during the transmission process, the algorithm adopts the theory of matrix decomposition to predict and supplement the missing forwarding capability value of nodes, thus improving the efficiency of message transmission. Simulation results show that compared with ITPCM algorithm, ETNS algorithm, Spray and Wait algorithm, and PRoPHET algorithm, the proposed scheme has the highest transmission success ratio and the lowest routing overhead.
Relation extraction tasks aim to predict potential relations between entities in a target sentence. As entity mentions have ambiguity in sentences, some important contextual information can guide the semantic representation of entity mentions to improve the accuracy of relation extraction. However, most existing relation extraction models ignore the semantic guidance of contextual information to entity mentions and treat entity mentions in and the textual context of a sentence equally. This results in low-accuracy relation extractions. To address this problem, we propose a contextual semantic-guided entity-centric graph convolutional network (CEGCN) model that enables entity mentions to obtain semantic-guided contextual information for more accurate relational representations. This model develops a self-attention enhanced neural network to concentrate on the importance and relevance of different words to obtain semantic-guided contextual information. Then, we employ a dependency tree with entities as global nodes and add virtual edges to construct an entity-centric logical adjacency matrix (ELAM). This matrix can enable entities to aggregate the semantic-guided contextual information with a one-layer GCN calculation. The experimental results on the TACRED and SemEval-2010 Task 8 datasets show that our model can efficiently use semantic-guided contextual information to enrich semantic entity representations and outperform previous models.
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.