Lune

EMNLP Findings2023

HFMRE: Constructing Huffman Tree in Bags to Find Excellent Instances for Distantly Supervised Relation Extraction

Min Li, Cong Shao, Gang Li, Mingle Zhou

Abstract

Since the introduction of distantly supervised relation extraction methods, numerous approaches have been developed, the most representative of which is multi-instance learning (MIL). To find reliable features that are most representative of multi-instance bags, aggregation strategies such as AVG (average), ONE (at least one), and ATT (sentence-level attention) are commonly used. These strategies tend to train third-party vectors to select sentence-level features, leaving it to the third party to decide/identify what is noise, ignoring the intrinsic associations that naturally exist from sentence to sentence. In this paper, we propose the concept of circular cosine similarity, which is used to explicitly show the intrinsic associations between sentences within a bag. We also consider the previous methods to be a crude denoising process as they are interrupted and do not have a continuous noise detection procedure. Following this consideration, we implement a relation extraction framework (HFMRE) that relies on the Huffman tree, where sentences are considered as leaf nodes and circular cosine similarity are considered as node weights. HFMRE can continuously and iteratively discriminate noise and aggregated features during the construction of the Huffman tree, eventually finding an excellent instance that is representative of a bag-level feature. The experiments demonstrate the remarkable effectiveness of our method, outperforming previously advanced baselines on the popular DSRE datasets.

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.

1 top-tier paper has 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

  • Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation Extraction cites Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction
  • Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation Extraction cites CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction
  • Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation Extraction cites HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction
  • HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction cites CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation ExtractionVipul Kumar Rathore, Malik Hammad Faisal, Parag Singla, MausamACL 2026

Builds on5

  1. HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation ExtractionDongyang Li, Taolin Zhang, Nan Hu, Chengyu Wang et al.ACL Findings 2022 · 48 citations
  2. Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation ExtractionTianyu Gao, Xu Han, Yuzhuo Bai, Keyue Qiu et al.ACL Findings 2021 · 29 citations
  3. High PE Utilization CNN Accelerator with Channel Fusion Supporting Pattern-Compressed Sparse Neural NetworksJingyu Wang, Songming Yu, Jinshan Yue, Zhe Yuan et al.DAC 2020 · 22 citations
  4. Coding Textual Inputs Boosts the Accuracy of Neural NetworksAbdul Rafae Khan, Jia Xu, Weiwei SunEMNLP 2020 · 2 citations
  5. CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation ExtractionTao Chen, Haizhou Shi, Siliang Tang, Zhigang Chen et al.ACL 2021

Related papers

  1. Distantly Supervised Relation Extraction using Multi-Layer Revision Network and Confidence-based Multi-Instance LearningXiangyu Lin, Tianyi Liu, Weijia Jia, Zhiguo GongEMNLP 2021 · 10 citations
  2. Noise-Robust Semi-Supervised Learning for Distantly Supervised Relation ExtractionXin Sun, Qiang Liu, Shu Wu, Zilei Wang et al.EMNLP Findings 2023 · 3 citations
  3. Are Noisy Sentences Useless for Distant Supervised Relation Extraction?Yuming Shang, He Yan Huang, Xianling Mao, Xin Sun et al.AAAI 2020 · 39 citations
  4. Empower Distantly Supervised Relation Extraction with Collaborative Adversarial TrainingTao Chen, Haochen Shi, Liyuan Liu, Siliang Tang et al.AAAI 2021 · 24 citations
  5. SENT: Sentence-level Distant Relation Extraction via Negative TrainingRuotian Ma, Tao Gui, Linyang Li, Qi Zhang et al.ACL 2021
Dusk over the sea between two cliffs drawn in fine vertical lines