Contextual Semantic-Guided Entity-Centric GCN for Relation Extraction

Long, Jun; Liu, Lei; Fei, Hongxiao; Xiang, Yiping; Li, Haoran; Huang, Wei‐Ping; Yang, Liu

doi:10.3390/math10081344

Cited by 6 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, the vector represented by the prototypes is obtained by weighting all prototype embeddings according to the similarity between the prototype embeddings and the sentence embeddings using the attention mechanism [9]. Specifically, the sentence representation obtained by PCNN is used as the query vector, and the cosine similarity between the sentence and each relation prototype is calculated by Equation (3), and then normalized by the softmax function to obtain the attention distribution of the input sentence over each relation prototype, as shown in Equation (4) [10] [11]. The information is selectively extracted from the prototype embedding by weighted summation according to the attention distribution to obtain the sentence vector represented by P h , as shown in Equation (5).…”

Section: Enhanced With Relation Prototype and Entity Typementioning

confidence: 99%

Long Tail Relation Extraction Enhanced with Prototype and Entity Type

Chen,

Cao,

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

To address the long-tail problem in distantsupervised datasets, this paper proposes a relation extraction model with relation prototypes and entity types to enhance the sentence representation. Based on the idea of prototype, information is selectively extracted from the prototype embedding to enhance the sentence representation through the attention mechanism, and the entity type information is incorporated into the sentence representation, so that implicit dependency paths are established between different relations through the relation prototypes and entity types. It also combines the constraint graph to explicitly model the potential semantic dependencies between different relations, further enhancing the model’s ability to extract long-tail relationships. The experimental results on the NYT dataset and Re-TACRED dataset show that the proposed method can significantly improve the performance of the model on long-tail relations.

show abstract

Section: Enhanced With Relation Prototype and Entity Typementioning

confidence: 99%

Long Tail Relation Extraction Enhanced with Prototype and Entity Type

Chen,

Cao,

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, graph convolutional network (GCN) stand out for their ability to handle non-Euclidean distance structure data [11,15,16] and have been increasingly noticed by scholars and applied to extract potential spatialtemporal properties in trafc fows [17][18][19][20][21]. For example, the difusion convolutional recurrent neural network (DCRNN) proposed by Li et al [22] adopted a sequence-to-sequence (Seq2Seq) model to extract spatialtemporal dependencies from past trafc fows for trafc prediction.…”

Section: Introductionmentioning

confidence: 99%

Attention-Based Gated Recurrent Graph Convolutional Network for Short-Term Traffic Flow Forecasting

Lou

et al. 2023

Journal of Mathematics

View full text Add to dashboard Cite

Traffic flow prediction is the basis of dynamic strategies and applications of intelligent transportation systems (ITS). Accurate traffic flow prediction is of great practical significance in alleviating road congestion and reducing urban road traffic safety hazards. It is challenging since the traffic flow has highly non-linear and complex patterns due to external factors such as time and space. Due to the high stochasticity and uncertainty of traffic flow, the difficulty of traffic flow prediction increases gradually with increasing time steps. The prediction performance of most existing short-term traffic flow prediction methods deteriorates rapidly for longer time steps. In addition, different methods are compared on the same time-granularity dataset, leaving the adaptability and robustness of these methods undervalidated. To address the above challenges, a new traffic forecasting method, named Attention-Based Gated Recurrent Graph Convolutional Network (AGRGCN) is presented for short-term traffic flow prediction. The method can extract spatialtemporal dependencies in traffic flow. In addition, an attention mechanism, which can adaptively capture traffic data relationships at different time steps, is introduced to alleviate the problem of faster deterioration of model prediction performance for longer time steps. Using a road network distance-based graph enables the method better to capture the topological information in traffic flow data. Experiments were conducted on two traffic datasets with different time granularity to predict traffic flow in highway and urban contexts. The experimental results show that our model has certain advantages.

show abstract

“…The proposed variant is named the Augmented Whale Optimization Algorithm (AWOA) and tests over two benchmark suits. Contribution [17] proposes 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, employs a dependency tree with entities as global nodes, and adds virtual edges to construct an entity-centric logical adjacency matrix (ELAM).…”

mentioning

confidence: 99%