{"type":"ScholarlyArticle","title":"KnowRA: Knowledge Retrieval Augmented Method for Document-level Relation Extraction with Comprehensive Reasoning Abilities","authors":[{"name":"Chengcheng Mai","slug":"chengcheng-mai","given":"Chengcheng","family":"Mai","affiliation":""},{"name":"Yuxiang Wang","slug":"yuxiang-wang","given":"Yuxiang","family":"Wang","affiliation":""},{"name":"Ziyu Gong","slug":"ziyu-gong","given":"Ziyu","family":"Gong","affiliation":""},{"name":"Hanxiang Wang","slug":"hanxiang-wang","given":"Hanxiang","family":"Wang","affiliation":""},{"name":"Yihua Huang","slug":"yihua-huang","given":"Yihua","family":"Huang","affiliation":""}],"abstract":"Document-level relation extraction (Doc-RE) aims to extract relations between entities across multiple sentences. Therefore, Doc-RE requires more comprehensive reasoning abilities like humans, involving complex cross-sentence interactions between entities, contexts, and external general knowledge, compared to the sentence-level RE. However, most existing Doc-RE methods focus on optimizing single reasoning ability, but lack the ability to utilize external knowledge for comprehensive reasoning on long documents. To solve these problems, a knowledge retrieval augmented method, named KnowRA, was proposed with comprehensive reasoning to autonomously determine whether to accept external knowledge to assist Doc-RE. Firstly, we constructed a document graph for semantic encoding and integrated the co-reference resolution model to augment the co-reference reasoning ability. Then, we expanded the document graph into a document knowledge graph by retrieving the external knowledge base for common-sense reasoning and a novel knowledge filtration method was presented to filter out irrelevant knowledge. Finally, we proposed the axis attention mechanism to build direct and indirect associations with intermediary entities for achieving cross-sentence logical reasoning. Extensive experiments conducted on two datasets verified the effectiveness of our method compared to the state-of-the-art baselines. Our code is available at https://anonymous.4open.science/r/KnowRA.","doi":"10.24963/ijcai.2025/910","url":"https://ijcai.org/proceedings/2025/910","pdf":"https://ijcai.org/proceedings/2025/0910.pdf","markdown":"https://ijcai.org/proceedings/2025/910.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/910","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Natural Language Processing","track":"Main Track","number":910,"pages":{"first":8186,"last":8194},"keywords":["Data Mining: DM: Mining text, web, social media","Natural Language Processing: NLP: Information extraction","Knowledge Representation and Reasoning: KRR: Common-sense reasoning","Natural Language Processing: NLP: Applications"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}