{"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/a-densely-connected-criss-cross-attention","title":"A Densely Connected Criss-Cross Attention Network for Document-level Relation Extraction","arxiv_id":"2203.13953","date":"2022-03-26","proceeding":null,"authors":["Liang Zhang","Yidong Cheng"],"abstract":"Document-level relation extraction (RE) aims to identify relations between two entities in a given document. Compared with its sentence-level counterpart, document-level RE requires complex reasoning. Previous research normally completed reasoning through information propagation on the mention-level or entity-level document-graph, but rarely considered reasoning at the entity-pair-level.In this paper, we propose a novel model, called Densely Connected Criss-Cross Attention Network (Dense-CCNet), for document-level RE, which can complete logical reasoning at the entity-pair-level. Specifically, the Dense-CCNet performs entity-pair-level logical reasoning through the Criss-Cross Attention (CCA), which can collect contextual information in horizontal and vertical directions on the entity-pair matrix to enhance the corresponding entity-pair representation. In addition, we densely connect multiple layers of the CCA to simultaneously capture the features of single-hop and multi-hop logical reasoning.We evaluate our Dense-CCNet model on three public document-level RE datasets, DocRED, CDR, and GDA. Experimental results demonstrate that our model achieves state-of-the-art performance on these three datasets.","url_abs":"https://arxiv.org/abs/2203.13953v1","url_pdf":"https://arxiv.org/pdf/2203.13953v1.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":"document-level-relation-extraction","task_name":"Document-level Relation Extraction"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-cdr","task":"Relation Extraction","dataset":"CDR","model":"Dense-CCNet-SciBERTbase","rank_in_archive_order":2,"of":10,"metrics":{"F1":"77.06"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-docred","task":"Relation Extraction","dataset":"DocRED","model":"Dense-CCNet-BERTbase","rank_in_archive_order":13,"of":62,"metrics":{"F1":"62.55","Ign F1":"60.46"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-gda","task":"Relation Extraction","dataset":"GDA","model":"Dense-CCNet-SciBERTbase","rank_in_archive_order":2,"of":9,"metrics":{"F1":"86.44"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.13953","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}