{"url":"/method/hegcn","slug":"hegcn","name":"HEGCN","full_name":"Hierarchical Entity Graph Convolutional Network","full_name_withheld":false,"description_markdown":"**HEGCN**, or **Hierarchical Entity Graph Convolutional Network** is a model for multi-hop relation extraction across documents. Documents in a document chain are encoded using a bi-directional long short-term memory ([BiLSTM](https://paperswithcode.com/method/bilstm)) layer. On top of the BiLSTM layer, two graph convolutional networks ([GCN](https://paperswithcode.com/method/gcn)) are used, one after another in a hierarchy. \r\n\r\nIn the first level of the GCN hierarchy, a separate entity mention graph is constructed on each document of the chain using all the entities mentioned in that document. Each mention of an entity in a document is considered as a separate node in the graph. A graph convolutional network (GCN) is used to represent the entity mention graph of each document to capture the relations among the entity mentions in the document. A unified entity-level graph is then constructed across all the documents in the chain. Each node of this entity-level graph represents a unique entity in the document chain. Each common entity between two documents in the chain is represented by a single node in the graph. A GCN is used to represent this entity-level graph to capture the relations among the entities across the documents. \r\n\r\nThe representations of the nodes of the subject entity and object entity are concatenated and passed to a feed-forward layer with [softmax](https://paperswithcode.com/method/softmax) for relation classification.","description_state":"present","introduced_year":null,"introduced_by":{"title":"A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents","paper":"/paper/a-hierarchical-entity-graph-convolutional","first_author":"Tapas Nayak","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/a-hierarchical-entity-graph-convolutional"},"source":{"url":"https://arxiv.org/abs/2108.09505v1","title":"A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Relation Extraction Models","url":"/methods/category/relation-extraction-models","pwc_aliases":[]},{"area":"Graphs","area_id":"graphs","collection":"Graph Models","url":"/methods/category/graph-models","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/a-hierarchical-entity-graph-convolutional","title":"A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents","date":"2021-08-21","arxiv_id":"2108.09505","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":null,"name":"Relation","papers":1},{"task":"/task/relation-extraction","name":"Relation Extraction","papers":1},{"task":"/task/sentence","name":"Sentence","papers":1}],"tasks_shown":3,"n_tasks":3,"usage_by_year":[{"year":"2021","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/hegcn"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}