Relation Extraction with Self-determined Graph Convolutional Network

Sunil Kumar SAHU, Derek THOMAS, Billy CHIU, Neha SENGUPTA, Mohammady MAHDY

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

10 Citations (Scopus)


Relation Extraction is a way of obtaining the semantic relationship between entities in text. The state-of-the-art methods use linguistic tools to build a graph for the text in which the entities appear and then a Graph Convolutional Network (GCN) is employed to encode the pre-built graphs. Although their performance is promising, the reliance on linguistic tools results in a non end-to-end process. In this work, we propose a novel model, the Self-determined Graph Convolutional Network (SGCN), which determines a weighted graph using a self-attention mechanism, rather using any linguistic tool. Then, the self-determined graph is encoded using a GCN. We test our model on the TACRED dataset and achieve the state-of-the-art result. Our experiments show that SGCN outperforms the traditional GCN, which uses dependency parsing tools to build the graph.
Original languageEnglish
Title of host publicationProceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM ’20)
PublisherAssociation for Computing Machinery (ACM)
ISBN (Print)9781450368599
Publication statusPublished - 19 Oct 2020
Externally publishedYes


Dive into the research topics of 'Relation Extraction with Self-determined Graph Convolutional Network'. Together they form a unique fingerprint.

Cite this