Search Results for author: Dongyu Zhang

Found 26 papers, 10 papers with code

基于HowNet的无监督汉语动词隐喻识别方法(Unsupervised Chinese Verb Metaphor Recognition Method Based on HowNet)

no code implementations CCL 2021 Minghao Zhang, Dongyu Zhang, Hongfei Lin

“隐喻是人类思维和语言理解的核心问题。随着互联网发展和海量文本出现, 利用自然语言处理技术对隐喻文本进行自动识别成为一种迫切的需求。但是目前在汉语隐喻识别研究中, 由于语义资源有限, 导致模型容易过拟合。此外, 主流隐喻识别方法存在可解释性差的缺点。针对上述问题, 本文构建了一个规模较大的汉语动词隐喻数据集, 并且提出了一种基于HowNet的无监督汉语动词隐喻识别模型。实验结果表明, 本文提出的模型能够有效地应用于动词隐喻识别任务, 识别效果超过了对比的无监督模型;并且, 与其它用于隐喻识别的深度学习模型相比, 本文模型具有结构简单、参数少、可解释性强的优点。”

Graph Transformers: A Survey

no code implementations13 Jul 2024 Ahsan Shehzad, Feng Xia, Shagufta Abid, Ciyuan Peng, Shuo Yu, Dongyu Zhang, Karin Verspoor

Graph transformers are a recent advancement in machine learning, offering a new class of neural network models for graph-structured data.

Diversity Graph Attention +1

Take its Essence, Discard its Dross! Debiasing for Toxic Language Detection via Counterfactual Causal Effect

1 code implementation3 Jun 2024 Junyu Lu, Bo Xu, Xiaokun Zhang, Kaiyuan Liu, Dongyu Zhang, Liang Yang, Hongfei Lin

Current methods of toxic language detection (TLD) typically rely on specific tokens to conduct decisions, which makes them suffer from lexical bias, leading to inferior performance and generalization.

counterfactual Counterfactual Inference +2

Enhancing Textual Personality Detection toward Social Media: Integrating Long-term and Short-term Perspectives

no code implementations23 Apr 2024 Haohao Zhu, Xiaokun Zhang, Junyu Lu, Youlin Wu, Zewen Bai, Changrong Min, Liang Yang, Bo Xu, Dongyu Zhang, Hongfei Lin

This limitation hinders a comprehensive understanding of individuals' personalities, as both stable traits and dynamic states are vital.

Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge

1 code implementation16 Dec 2023 Conghan Yue, Zhengwei Peng, Junlong Ma, Shiyan Du, Pengxu Wei, Dongyu Zhang

By leveraging the natural mean-reverting property of the generalized OU process and further eliminating the variance of its steady-state distribution through the Doob's h-transform, we achieve diffusion mappings from point to point enabling the recovery of high-quality images from low-quality ones.

Image Inpainting Image Restoration +2

UCE-FID: Using Large Unlabeled, Medium Crowdsourced-Labeled, and Small Expert-Labeled Tweets for Foodborne Illness Detection

no code implementations2 Dec 2023 Ruofan Hu, Dongyu Zhang, Dandan Tao, Huayi Zhang, Hao Feng, Elke Rundensteiner

To overcome these challenges, we propose EGAL, a deep learning framework for foodborne illness detection that uses small expert-labeled tweets augmented by crowdsourced-labeled and massive unlabeled data.

EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE

no code implementations23 Aug 2023 Junyi Chen, Longteng Guo, Jia Sun, Shuai Shao, Zehuan Yuan, Liang Lin, Dongyu Zhang

Owing to the combination of the unified architecture and pre-training task, EVE is easy to scale up, enabling better downstream performance with fewer resources and faster training speed.

Image-text matching Image-text Retrieval +5

TWEET-FID: An Annotated Dataset for Multiple Foodborne Illness Detection Tasks

no code implementations LREC 2022 Ruofan Hu, Dongyu Zhang, Dandan Tao, Thomas Hartvigsen, Hao Feng, Elke Rundensteiner

To accelerate the development of machine learning-based models for foodborne outbreak detection, we thus present TWEET-FID (TWEET-Foodborne Illness Detection), the first publicly available annotated dataset for multiple foodborne illness incident detection tasks.

slot-filling Slot Filling

Surf or sleep? Understanding the influence of bedtime patterns on campus

no code implementations18 Feb 2022 Teng Guo, Linhong Li, Dongyu Zhang, Feng Xia

In this paper, we develop a general data-driven method for identifying students' sleep patterns according to their Internet access pattern stored in the education management system and explore its influence from various aspects.


Instant Response Few-shot Object Detection with Meta Strategy and Explicit Localization Inference

1 code implementation26 Oct 2021 Junying Huang, Fan Chen, Sibo Huang, Dongyu Zhang

Specifically, we first propose two simple but effective meta-strategies for the box classifier and RPN module to enable the object detection of novel categories with instant response.

Few-Shot Learning Few-Shot Object Detection +2

MultiMET: A Multimodal Dataset for Metaphor Understanding

no code implementations ACL 2021 Dongyu Zhang, Minghao Zhang, Heting Zhang, Liang Yang, Hongfei Lin

Metaphor involves not only a linguistic phenomenon, but also a cognitive phenomenon structuring human thought, which makes understanding it challenging.

Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking

1 code implementation CVPR 2020 Hongjun Wang, Guangrun Wang, Ya Li, Dongyu Zhang, Liang Lin

To examine the robustness of ReID systems is rather important because the insecurity of ReID systems may cause severe losses, e. g., the criminals may use the adversarial perturbations to cheat the CCTV systems.

Adversarial Attack Person Re-Identification

Graduate Employment Prediction with Bias

no code implementations27 Dec 2019 Teng Guo, Feng Xia, Shihao Zhen, Xiaomei Bai, Dongyu Zhang, Zitao Liu, Jiliang Tang

The failure of landing a job for college students could cause serious social consequences such as drunkenness and suicide.

Generative Adversarial Network

Telling the Whole Story: A Manually Annotated Chinese Dataset for the Analysis of Humor in Jokes

no code implementations IJCNLP 2019 Dongyu Zhang, Heting Zhang, Xikai Liu, Hongfei Lin, Feng Xia

To the best of our knowledge, we are the first to approach humor annotation for exploring the underlying mechanism of the use of humor, which may contribute to a significantly deeper analysis of humor.

A Knowledge Graph Based Solution for Entity Discovery and Linking in Open-Domain Questions

no code implementations5 Dec 2018 Kai Lei, Bing Zhang, Yong liu, Yang Deng, Dongyu Zhang, Ying Shen

In Question Entity Discovery and Linking (QEDL) problem, traditional methods are challenged because multiple entities in one short question are difficult to be discovered entirely and the incomplete information in short text makes entity linking hard to implement.

Entity Linking Learning-To-Rank +5

WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition

no code implementations EMNLP 2018 Yufeng Diao, Hongfei Lin, Di wu, Liang Yang, Kan Xu, Zhihao Yang, Jian Wang, Shaowu Zhang, Bo Xu, Dongyu Zhang

In this work, we first use WordNet to understand and expand word embedding for settling the polysemy of homographic puns, and then propose a WordNet-Encoded Collocation-Attention network model (WECA) which combined with the context weights for recognizing the puns.

Construction of a Chinese Corpus for the Analysis of the Emotionality of Metaphorical Expressions

no code implementations ACL 2018 Dongyu Zhang, Hongfei Lin, Liang Yang, Shaowu Zhang, Bo Xu

However, there is little research on the construction of metaphor corpora annotated with emotion for the analysis of emotionality of metaphorical expressions.

Emotion Recognition

Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteria

1 code implementation30 Jun 2018 Keze Wang, Liang Lin, Xiaopeng Yan, Ziliang Chen, Dongyu Zhang, Lei Zhang

The proposed process can be compatible with mini-batch based training (i. e., using a batch of unlabeled or partially labeled data as a one-time input) for object detection.

Active Learning object-detection +2

Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection

no code implementations CVPR 2018 Keze Wang, Xiaopeng Yan, Dongyu Zhang, Lei Zhang, Liang Lin

Though quite challenging, leveraging large-scale unlabeled or partially labeled images in a cost-effective way has increasingly attracted interests for its great importance to computer vision.

Active Learning Object +2

Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning

no code implementations4 Oct 2017 Dongyu Zhang, Liang Lin, Tianshui Chen, Xian Wu, Wenwei Tan, Ebroul Izquierdo

Sketch portrait generation benefits a wide range of applications such as digital entertainment and law enforcement.

Representation Learning

Cost-Effective Active Learning for Deep Image Classification

3 code implementations13 Jan 2017 Keze Wang, Dongyu Zhang, Ya Li, Ruimao Zhang, Liang Lin

In this paper, we propose a novel active learning framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner.

Active Learning Classification +5

Cannot find the paper you are looking for? You can Submit a new open access paper.