Lune

ACL Findings2022

Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion

Yiqing Xie, Jiaming Shen, Sha Li, Yuning Mao, Jiawei Han

Abstract

Document-level relation extraction (DocRE)aims to extract semantic relations among entity pairs in a document.Typical DocRE methods blindly take the full document as input, while a subset of the sentences in the document, noted as the evidence, are often sufficient for humans to predict the relation of an entity pair.In this paper, we propose an evidenceenhanced framework, EIDER, that empowers DocRE by efficiently extracting evidence and effectively fusing the extracted evidence in inference.1 We first jointly train an RE model with a lightweight evidence extraction model, which is efficient in both memory and runtime.Empirically, even training the evidence model on silver labels constructed by our heuristic rules can lead to better RE performance.We further design a simple yet effective inference process that makes RE predictions on both extracted evidence and the full document, then fuses the predictions through a blending layer.This allows EIDER to focus on important sentences while still having access to the complete information in the document.Extensive experiments show that EIDER outperforms state-ofthe-art methods on three benchmark datasets (e.g., by 1.37/1.26Ign F1/F1 on DocRED).Head:Hero of the Day Tail:the United States Rel:[country of origin] GT evidence sentences: [1,10] Extracted evidence: [1,10] Original document as input: [1] Load is the sixth studio album by the American heavy metal band Metallica, released on June 4, 1996 by Elektra Records in the United States … [9] It was certified 5×platinum … for shipping five million copies in the United States.[10] Four singles-"Hero of the Day", "Until It Sleeps", "Mama Said", and "King Nothing" -were released as part of the marketing campaign for the album.Prediction scores: NA: 17.63 country of origin: 14.79 Extracted evidence as input: [1] Load is the sixth studio album … released … in the United States … [10] Four singles -"Hero of the Day", … were released … for the album.Prediction scores: country of origin: 18.31 NA: 13.45 Final prediction of our model: country of origin (✓)

Ask Lune

Ask anything. The answer quotes the paper.

Lune reads all of it and the papers around it, then shows you the passages behind every answer.

Questions to start from

Lune answers from

the full paper · 9 top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Cited by top-tier papers9

  1. A Novel Table-to-Graph Generation Approach for Document-Level Joint Entity and Relation ExtractionRuoyu Zhang, Yanzeng Li, Lei ZouACL 2023 · 20 citations
  2. Revisiting Document-Level Relation Extraction with Context-Guided Link PredictionMonika Jain, Raghava Mutharaju, Ramakanth Kavuluru, Kuldeep SinghAAAI 2024 · 17 citations
  3. Anaphor Assisted Document-Level Relation ExtractionChonggang Lu, Richong Zhang, Kai Sun, Jaein Kim et al.EMNLP 2023 · 16 citations
  4. HistRED: A Historical Document-Level Relation Extraction DatasetSoyoung Yang, Minseok Choi, Youngwoo Cho, Jaegul ChooACL 2023 · 9 citations
  5. Boosting Document-Level Relation Extraction by Mining and Injecting Logical RulesShengda Fan, Shasha Mo, Jianwei NiuEMNLP 2022 · 9 citations

Builds on7

  1. Document-Level Relation Extraction with Adaptive Thresholding and Localized Context PoolingWenxuan Zhou, Kevin Huang, Tengyu Ma, Jing HuangAAAI 2021 · 360 citations
  2. Reasoning with Latent Structure Refinement for Document-Level Relation ExtractionGuoshun Nan, Zhijiang Guo, Ivan Sekulic, Wei LuACL 2020 · 294 citations
  3. Double Graph Based Reasoning for Document-level Relation ExtractionShuang Zeng, Runxin Xu, Baobao Chang, Lei LiEMNLP 2020 · 238 citations
  4. Coreferential Reasoning Learning for Language RepresentationDeming Ye, Yankai Lin, Jiaju Du, Zhenghao Liu et al.EMNLP 2020 · 164 citations
  5. Document-Level Relation Extraction with ReconstructionWang Xu, Kehai Chen, Tiejun ZhaoAAAI 2021 · 131 citations

Related papers

  1. SRF: Enhancing Document-Level Relation Extraction with a Novel Secondary Reasoning FrameworkFu Zhang, Qi Miao, Jingwei Cheng, Hongsen Yu et al.EMNLP 2024 · 2 citations
  2. ET-MIER: Entity Type-guided Key Mention Identification and Evidence Retrieval for Document-level Relation ExtractionXin Li, Huangming Xu, Fu Zhang, Jingwei ChengEMNLP Findings 2025
  3. Not Just Plain Text! Fuel Document-Level Relation Extraction with Explicit Syntax Refinement and Subsentence ModelingZhichao Duan, Xiuxing Li, Zhenyu Li, Zhuo Wang et al.EMNLP Findings 2022 · 8 citations
  4. Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge DistillationQingyu Tan, Ruidan He, Lidong Bing, Hwee Tou NgACL Findings 2022 · 136 citations
  5. Towards Better Document-level Relation Extraction via Iterative InferenceLiang Zhang, Jinsong Su, Yidong Chen, Zhongjian Miao et al.EMNLP 2022 · 11 citations
Dusk over the sea between two cliffs drawn in fine vertical lines