paper-with-me

홈 › Papers

Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision

2022-05-18 · Zhen Wan, Fei Cheng, Qianying Liu, Zhuoyuan Mao, Haiyue Song, Sadao Kurohashi

Contrastive pre-training on distant supervision has shown remarkable effectiveness in improving supervised relation extraction tasks. However, the existing methods ignore the intrinsic noise of distant supervision during the pre-training stage. In this paper, we propose a weighted contrastive learning method by leveraging the supervised data to estimate the reliability of pre-training instances and explicitly reduce the effect of noise. Experimental results on three supervised datasets demonstrate the advantages of our proposed weighted contrastive learning approach compared to two state-of-the-art non-weighted baselines.Our code and models are available at: https://github.com/YukinoWan/WCL

📄 PDF Abstract BibTeX arXiv:2205.08770

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningRelationRelation Extraction

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction

2022-02-27 · Findings (ACL) 2022 5 · Dongyang Li, Taolin Zhang, Nan Hu, Chengyu Wang 외

Distant supervision assumes that any sentence containing the same entity pairs reflects identical relationships. Previous works of distantly supervised relation extraction (DSRE) task generally focus on sentence-level or…

Contrastive LearningData AugmentationRelationRelation Extraction+1

Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention

2018-04-19 · Sharmistha Jat, Siddhesh Khandelwal, Partha Talukdar

Relation extraction is the problem of classifying the relationship between two entities in a given sentence. Distant Supervision (DS) is a popular technique for developing relation extractors starting with limited superv…

RelationRelation ExtractionRelationship Extraction (Distant Supervised)Sentence

A class-weighted supervised contrastive learning long-tailed bearing fault diagnosis approach using quadratic neural network

2023-09-21 · Wei-En Yu, Jinwei Sun, Shiping Zhang, Xiaoge Zhang 외

Deep learning has achieved remarkable success in bearing fault diagnosis. However, its performance oftentimes deteriorates when dealing with highly imbalanced or long-tailed data, while such cases are prevalent in indust…

Contrastive LearningData AugmentationFault Diagnosis

CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction

2021-06-21 · ACL 2021 5 · Tao Chen, Haizhou Shi, Siliang Tang, Zhigang Chen 외

The journey of reducing noise from distant supervision (DS) generated training data has been started since the DS was first introduced into the relation extraction (RE) task. For the past decade, researchers apply the mu…

RelationRelation ExtractionSentence

Fine-grained Contrastive Learning for Relation Extraction

2022-05-25 · William Hogan, Jiacheng Li, Jingbo Shang

Recent relation extraction (RE) works have shown encouraging improvements by conducting contrastive learning on silver labels generated by distant supervision before fine-tuning on gold labels. Existing methods typically…

Contrastive LearningDenoisingLanguage ModelingLanguage Modelling+2