{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/efficient-long-distance-relation-extraction","title":"Efficient long-distance relation extraction with DG-SpanBERT","arxiv_id":"2004.03636","date":"2020-04-07","proceeding":"Conference 2020 4","authors":["Jun Chen","Robert Hoehndorf","Mohamed Elhoseiny","Xiangliang Zhang"],"abstract":"In natural language processing, relation extraction seeks to rationally understand unstructured text. Here, we propose a novel SpanBERT-based graph convolutional network (DG-SpanBERT) that extracts semantic features from a raw sentence using the pre-trained language model SpanBERT and a graph convolutional network to pool latent features. Our DG-SpanBERT model inherits the advantage of SpanBERT on learning rich lexical features from large-scale corpus. It also has the ability to capture long-range relations between entities due to the usage of GCN on dependency tree. The experimental results show that our model outperforms other existing dependency-based and sequence-based models and achieves a state-of-the-art performance on the TACRED dataset.","url_abs":"https://arxiv.org/abs/2004.03636v1","url_pdf":"https://arxiv.org/pdf/2004.03636v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"gcn","method_name":"GCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-tacred","task":"Relation Extraction","dataset":"TACRED","model":"DG-SpanBERT-large","rank_in_archive_order":19,"of":40,"metrics":{"F1":"71.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.03636","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}