paper-with-me

Papers

MultiEM: Efficient and Effective Unsupervised Multi-Table Entity Matching

2023-08-02 · Xiaocan Zeng, Pengfei Wang, YUREN MAO, Lu Chen, Xiaoze Liu, Yunjun Gao

Entity Matching (EM), which aims to identify all entity pairs referring to the same real-world entity from relational tables, is one of the most important tasks in real-world data management systems. Due to the labeling process of EM being extremely labor-intensive, unsupervised EM is more applicable than supervised EM in practical scenarios. Traditional unsupervised EM assumes that all entities come from two tables; however, it is more common to match entities from multiple tables in practical applications, that is, multi-table entity matching (multi-table EM). Unfortunately, effective and efficient unsupervised multi-table EM remains under-explored. To fill this gap, this paper formally studies the problem of unsupervised multi-table entity matching and proposes an effective and efficient solution, termed as MultiEM. MultiEM is a parallelable pipeline of enhanced entity representation, table-wise hierarchical merging, and density-based pruning. Extensive experimental results on six real-world benchmark datasets demonstrate the superiority of MultiEM in terms of effectiveness and efficiency.

📄 PDF Abstract BibTeX arXiv:2308.01927

Code (1)

zju-daily/multiem 공식 구현

Tasks

Management

Similar Papers 제목 키워드 기반

FedMultiEmo: Real-Time Emotion Recognition via Multimodal Federated Learning

2025-07-21 · Baran Can Gül, Suraksha Nadig, Stefanos Tziampazis, Nasser Jazdi 외 arxiv

In-vehicle emotion recognition underpins adaptive driver-assistance systems and, ultimately, occupant safety. However, practical deployment is hindered by (i) modality fragility - poor lighting and occlusions degrade vis…

Emotion RecognitionFederated Learning

Entity Set Search of Scientific Literature: An Unsupervised Ranking Approach

2018-04-29 · Jiaming Shen, Jinfeng Xiao, Xinwei He, Jingbo Shang 외

Literature search is critical for any scientific research. Different from Web or general domain search, a large portion of queries in scientific literature search are entity-set queries, that is, multiple entities of pos…

Model Selection

Unsupervised Incremental Learning of Deep Descriptors From Video Streams

2017-08-11 · Federico Pernici, Alberto del Bimbo

We present a novel unsupervised method for face identity learning from video sequences. The method exploits the ResNet deep network for face detection and VGGface fc7 face descriptors together with a smart learning mecha…

Face DetectionIncremental Learning

Learning Identity-Invariant Motion Representations for Cross-ID Face Reenactment

2020-06-01 · CVPR 2020 6 · Po-Hsiang Huang, Fu-En Yang, Yu-Chiang Frank Wang

Human face reenactment aims at transferring motion patterns from one face (from a source-domain video) to an-other (in the target domain with the identity of interest).While recent works report impressive results, they a…

Face Reenactment

Unsupervised Paraphrasing Consistency Training for Low Resource Named Entity Recognition

2021-11-01 · EMNLP 2021 11 · Rui Wang, Ricardo Henao

Unsupervised consistency training is a way of semi-supervised learning that encourages consistency in model predictions between the original and augmented data. For Named Entity Recognition (NER), existing approaches aug…

Data AugmentationLow Resource Named Entity RecognitionMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION+4