Joint Type Inference on Entities and Relations via Graph Convolutional Networks

Abstract

We develop a new paradigm for the task of joint entity relation extraction. It first identifies entity spans, then performs a joint inference on entity types and relation types. To tackle the joint type inference task, we propose a novel graph convolutional network (GCN) running on an entity-relation bipartite graph. By introducing a binary relation classification task, we are able to utilize the structure of entity-relation bipartite graph in a more efficient and interpretable way. Experiments on ACE05 show that our model outperforms existing joint models in entity performance and is competitive with the state-of-the-art in relation performance.

Improving Graph Convolutional Networks Based on Relation-Aware Attention for End-to-End Relation Extraction

“…Zeng et al [14] applies copy mechanism to solve the overlapping relations extraction problem, but this work fails to extract multi-word entities. Sun et al [12] and Fu et al [15] construct a graph which is encoded by GCN to extract relations from one sentence. Zhou et al [34] applied reinforcement learning to remove the noisy data from the training dataset to enhance extraction.…”

“…Entities and relations between them in a sentence can form a graph. However, most existing methods [12], [15] ignore relations information between two connected entities in a graph. To tackle these problems, we propose a novel attention module called relation-aware attention mechanism for the purpose of obtaining relation representation over all entity span pairs.…”

“…AntNRE [12]: an approach that constructs an entity-relation bipartite graph with detected entity spans.…”

“…Some researches have solved overlapping relations problem, but different shortcomings exists. Sun et al [12] defines an entity-relation bipartite graph, however the performance is affected by the performance of relation identification. Besides, models employing GCN [13] are proposed.…”

Stacked Mixed-Order Graph Convolutional Networks for Collaborative Filtering

“…Graph-based models explore the local and global topological structure of the user-item graph combined with other attributes, and aim to learn efficient low-dimensional representations for each user and item. Graph Convolutional Networks(GCNs) [7] and its variants [4,[19][20][21] extend deep learning algorithms to graph-structured data by defining convolution operators on graphs, and have proven powerful when dealing with various downstream tasks [3,13,17,22], including learning low-dimensional embeddings of users and items in a recommender system [19,21,26]. However, such models struggle to capture higher-order connectivity patterns among nodes, as they only aggregate information from direct neighboring nodes (or firstorder neighbors), though it could be beneficial to take high-order connectivity into account [8,15].…”