Cost-sensitive Regularization for Label Confusion-aware Event Detection

2019-06-14 · ACL 2019 7 · Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun

In supervised event detection, most of the mislabeling occurs between a small number of confusing type pairs, including trigger-NIL pairs and sibling sub-types of the same coarse type. To address this label confusion problem, this paper proposes cost-sensitive regularization, which can force the training procedure to concentrate more on optimizing confusing type pairs. Specifically, we introduce a cost-weighted term into the training loss, which penalizes more on mislabeling between confusing label pairs. Furthermore, we also propose two estimators which can effectively measure such label confusion based on instance-level or population-level statistics. Experiments on TAC-KBP 2017 datasets demonstrate that the proposed method can significantly improve the performances of different models in both English and Chinese event detection.

📄 PDF Abstract BibTeX arXiv:1906.06003

Code (1)

sanmusunrise/CSR 공식 구현 tf

Tasks

Event DetectionVocal Bursts Type Prediction

DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation

2026-01-31 · Yingxu Wang, Xinwang Liu, Mengzhu Wang, Siyang Gao 외 arxiv

Graph Domain Adaptation (GDA) aims to transfer graph classifiers across domains with both semantic and topological shifts. Existing Euclidean adversarial methods face two challenges: Structural Degeneration, where domain…

Representation Learning GRAPH DOMAIN ADAPTATION

Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion

2019-02-10 · CVPR 2019 6 · Ryutaro Tanno, Ardavan Saeedi, Swami Sankaranarayanan, Daniel C. Alexander 외

The predictive performance of supervised learning algorithms depends on the quality of labels. In a typical label collection process, multiple annotators provide subjective noisy estimates of the "truth" under the influe…

image-classification Image Classification

Repairing Group-Level Errors for DNNs Using Weighted Regularization

2022-03-24 · Ziyuan Zhong, Yuchi Tian, Conor J. Sweeney, Vicente Ordonez 외

Deep Neural Networks (DNNs) have been widely used in software making decisions impacting people's lives. However, they have been found to exhibit severe erroneous behaviors that may lead to unfortunate outcomes. Previous…

Closing the Confusion Loop: CLIP-Guided Alignment for Source-Free Domain Adaptation

2026-02-09 · Shanshan Wang, Ziying Feng, Xiaozheng Shen, Xun Yang 외 arxiv

Source-Free Domain Adaptation (SFDA) tackles the problem of adapting a pre-trained source model to an unlabeled target domain without accessing any source data, which is quite suitable for the field of data security. Alt…

Source-Free Domain Adaptation Contrastive Learning

Improving Recommendation Fairness without Sensitive Attributes Using Multi-Persona LLMs

2025-05-26 · Haoran Xin, Ying Sun, Chao Wang, Yanke Yu 외

Despite the success of recommender systems in alleviating information overload, fairness issues have raised concerns in recent years, potentially leading to unequal treatment for certain user groups. While efforts have b…

Fairness Recommendation Systems Representation Learning