Lune

ACL Findings2023

Multi-hop Evidence Retrieval for Cross-document Relation Extraction

Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen

Abstract

Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document. This inevitably brings the challenge of efficient open-space evidence retrieval to support the inference of cross-document relations, along with the challenge of multi-hop reasoning on top of entities and evidence scattered in an open set of documents. To combat these challenges, we propose MR.COD (Multi-hop evidence retrieval for Cross-document relation extraction), which is a multi-hop evidence retrieval method based on evidence path mining and ranking. We explore multiple variants of retrievers to show evidence retrieval is essential in cross-document RE. We also propose a contextual dense retriever for this setting. Experiments on CodRED show that evidence retrieval with MR.COD effectively acquires crossdocument evidence and boosts end-to-end RE performance in both closed and open settings. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Reward-based Input Construction for Cross-document Relation Extraction cites Double Graph Based Reasoning for Document-level Relation Extraction
  • Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation cites Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling
  • Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation cites Double Graph Based Reasoning for Document-level Relation Extraction
  • DEBAR: Mitigating Contextual Bias in Cross-Document Relation Extraction via Dual-Stream Decoupling cites Reward-based Input Construction for Cross-document Relation Extraction
  • DEBAR: Mitigating Contextual Bias in Cross-Document Relation Extraction via Dual-Stream Decoupling cites Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling
  • DEBAR: Mitigating Contextual Bias in Cross-Document Relation Extraction via Dual-Stream Decoupling cites Double Graph Based Reasoning for Document-level Relation Extraction
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language ModelsMingyu Derek Ma, Xiaoxuan Wang, Po-Nien Kung, P. Jeffrey Brantingham et al.AAAI 2024 · 22 citations
  2. Reward-based Input Construction for Cross-document Relation ExtractionByeonghu Na, Suhyeon Jo, Yeongmin Kim, Il-Chul MoonACL 2024 · 3 citations
  3. HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific LiteratureDevvrat Joshi, Islem RekikICLR 2026 · 1 citation
  4. DEBAR: Mitigating Contextual Bias in Cross-Document Relation Extraction via Dual-Stream DecouplingZhixuan Yang, Fu Zhang, Huangming Xu, Jingwei ChengACL 2026

Builds on15

  1. Document-Level Relation Extraction with Adaptive Thresholding and Localized Context PoolingWenxuan Zhou, Kevin Huang, Tengyu Ma, Jing HuangAAAI 2021 · 360 citations
  2. Double Graph Based Reasoning for Document-level Relation ExtractionShuang Zeng, Runxin Xu, Baobao Chang, Lei LiEMNLP 2020 · 238 citations
  3. Knowledge-Grounded Dialogue Generation with Pre-trained Language ModelsXueliang Zhao, Wei Wu, Can Xu, Chongyang Tao et al.EMNLP 2020 · 153 citations
  4. Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations
  5. Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge DistillationQingyu Tan, Ruidan He, Lidong Bing, Hwee Tou NgACL Findings 2022 · 136 citations

Related papers

  1. Entity-centered Cross-document Relation ExtractionFengqi Wang, Fei Li, Hao Fei, Jingye Li et al.EMNLP 2022 · 49 citations
  2. CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the WildYuan Yao, Jiaju Du, Yankai Lin, Peng Li et al.EMNLP 2021 · 18 citations
  3. Knowledge-Driven Cross-Document Relation ExtractionMonika Jain, Raghava Mutharaju, Kuldeep Singh, Ramakanth KavuluruACL Findings 2024 · 5 citations
  4. SegDRE: A Salient Entity Guided Approach to Document-Level Relation ExtractionXing Yang, Chengxiang TanACL Findings 2026
  5. HopRetriever: Retrieve Hops over Wikipedia to Answer Complex QuestionsShaobo Li, Xiaoguang Li, Lifeng Shang, Xin Jiang et al.AAAI 2021 · 36 citations
Dusk over the sea between two cliffs drawn in fine vertical lines