paper-with-me

홈 › Papers

基于知识监督的标签降噪实体对齐(Refined De-noising for Labeled Entity Alignment from Auxiliary Evidence Knowledge)

2022-10-01 · CCL 2022 10 · Fenglong Su, Ning Jing

“大多数现有的实体对齐解决方案都依赖于干净的标记数据来训练模型,很少关注种子噪声。为了解决实体对齐中的噪声问题,本文提出了一个标签降噪框架,在实体对齐中注入辅助知识和附带监督,以纠正标记和引导过程中的种子错误。特别是,考虑到以前基于邻域嵌入方法的弱点,本文应用了一种新的对偶关系注意力匹配编码器来加速知识图谱的结构学习,同时使用辅助知识来弥补结构表征的不足。然后,通过对抗训练来执行弱监督标签降噪。对于误差累积的问题,本文进一步使用对齐精化模块来提高模型的性能。实验结果表明,所提的框架能够轻松应对含噪声环境下的实体对齐问题,在多个真实数据集上的对齐准确性和噪声辨别能力始终优于其他基线方法。”

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Entity Alignment

Similar Papers 제목 키워드 기반

Improving Pseudo Labels with Global-Local Denoising Framework for Cross-lingual Named Entity Recognition

2024-06-03 · Zhuojun Ding, Wei Wei, Xiaoye Qu, Dangyang Chen

Cross-lingual named entity recognition (NER) aims to train an NER model for the target language leveraging only labeled source language data and unlabeled target language data. Prior approaches either perform label proje…

Cross-Lingual NERDenoisingnamed-entity-recognitionNamed Entity Recognition+2

Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined Knowledge

2023-05-20 · Jinyuan Li, Han Li, Zhuo Pan, Di Sun 외

Multimodal Named Entity Recognition (MNER) on social media aims to enhance textual entity prediction by incorporating image-based clues. Existing studies mainly focus on maximizing the utilization of pertinent image info…

Multi-modal Named Entity Recognitionnamed-entity-recognitionNamed Entity Recognition

StableAnimator: High-Quality Identity-Preserving Human Image Animation

2024-11-26 · CVPR 2025 1 · Shuyuan Tu, Zhen Xing, Xintong Han, Zhi-Qi Cheng 외

Current diffusion models for human image animation struggle to ensure identity (ID) consistency. This paper presents StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-qu…

DenoisingFace ReenactmentHuman AnimationImage Animation+2

Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases

2024-03-16 · Hang Yin, Liyao Xiang, Dong Ding, Yuheng He 외

We investigate the entity alignment (EA) problem with unlabeled dangling cases, meaning that partial entities have no counterparts in the other knowledge graph (KG), and this type of entity remains unlabeled. To address …

Contrastive LearningEntity AlignmentRepresentation Learning

Combating Confirmation Bias: A Unified Pseudo-Labeling Framework for Entity Alignment

2023-07-05 · Qijie Ding, Jie Yin, Daokun Zhang, Junbin Gao

Entity alignment (EA) aims at identifying equivalent entity pairs across different knowledge graphs (KGs) that refer to the same real-world identity. To circumvent the shortage of seed alignments provided for training, r…

Entity AlignmentKnowledge GraphsPseudo Label