Search Results for author: Zhiqiang Wang

Found 22 papers, 12 papers with code

基于Self-Attention的句法感知汉语框架语义角色标注(Syntax-Aware Chinese Frame Semantic Role Labeling Based on Self-Attention)

no code implementations CCL 2020 Xiaohui Wang, Ru Li, Zhiqiang Wang, Qinghua Chai, Xiaoqi Han

框架语义角色标注(Frame Semantic Role Labeling, FSRL)是基于FrameNet标注体系的语义分析任务。语义角色标注通常对句法有很强的依赖性, 目前的语义角色标注模型大多基于双向长短时记忆网络Bi-LSTM, 虽然可以获取句子中的长距离依赖信息, 但无法很好获取句子中的句法信息。因此, 引入self-attention机制来捕获句子中每个词的句法信息。实验结果表明, 该模型在CFN(Chinese FrameNet, 汉语框架网)数据集上的F1达到83. 77%, 提升了近11%。

Semantic Role Labeling

Global Data Constraints: Ethical and Effectiveness Challenges in Large Language Model

1 code implementation17 Jun 2024 Jin Yang, Zhiqiang Wang, Yanbin Lin, Zunduo Zhao

The efficacy and ethical integrity of large language models (LLMs) are profoundly influenced by the diversity and quality of their training datasets.

Diversity Language Modelling +1

LLMGeo: Benchmarking Large Language Models on Image Geolocation In-the-wild

1 code implementation30 May 2024 Zhiqiang Wang, Dejia Xu, Rana Muhammad Shahroz Khan, Yanbin Lin, Zhiwen Fan, Xingquan Zhu

Inspired by the exceptional background knowledge of multimodal language models, we systematically evaluate their geolocation capabilities using a novel image dataset and a comprehensive evaluation framework.


Smart Expert System: Large Language Models as Text Classifiers

1 code implementation17 May 2024 Zhiqiang Wang, Yiran Pang, Yanbin Lin

Text classification is a fundamental task in Natural Language Processing (NLP), and the advent of Large Language Models (LLMs) has revolutionized the field.

Multi-Label Classification Sentiment Analysis +2

Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs

no code implementations15 Apr 2024 Ruoxi Cheng, Haoxuan Ma, Shuirong Cao, Jiaqi Li, Aihua Pei, Zhiqiang Wang, Pengliang Ji, Haoyu Wang, Jiaqi Huo

Based on this, we propose Reinforcement Learning from Multi-role Debates as Feedback (RLDF), a novel approach for bias mitigation replacing human feedback in traditional RLHF.

Bias Detection Logical Reasoning +1

Large Language Models Are Zero-Shot Text Classifiers

1 code implementation2 Dec 2023 Zhiqiang Wang, Yiran Pang, Yanbin Lin

Retrained large language models (LLMs) have become extensively used across various sub-disciplines of natural language processing (NLP).

text-classification Text Classification +1

Counting Manatee Aggregations using Deep Neural Networks and Anisotropic Gaussian Kernel

1 code implementation4 Nov 2023 Zhiqiang Wang, Yiran Pang, Cihan Ulus, Xingquan Zhu

In this paper, we propose a deep learning based crowd counting approach to automatically count number of manatees within a region, by using low quality images as input.

Crowd Counting Scene Recognition +1

Adaptive Neural Ranking Framework: Toward Maximized Business Goal for Cascade Ranking Systems

no code implementations16 Oct 2023 Yunli Wang, Zhiqiang Wang, Jian Yang, Shiyang Wen, Dongying Kong, Han Li, Kun Gai

Concretely, we employ multi-task learning to adaptively combine the optimization of relaxed and full targets, which refers to metrics Recall@m@k and OPA respectively.

Learning-To-Rank Multi-Task Learning +1

KGTrust: Evaluating Trustworthiness of SIoT via Knowledge Enhanced Graph Neural Networks

no code implementations22 Feb 2023 Zhizhi Yu, Di Jin, Cuiying Huo, Zhiqiang Wang, Xiulong Liu, Heng Qi, Jia Wu, Lingfei Wu

Graph neural networks for trust evaluation typically adopt a straightforward way such as one-hot or node2vec to comprehend node characteristics, which ignores the valuable semantic knowledge attached to nodes.

Graph Neural Network

Benchmarks for Corruption Invariant Person Re-identification

1 code implementation1 Nov 2021 Minghui Chen, Zhiqiang Wang, Feng Zheng

When deploying person re-identification (ReID) model in safety-critical applications, it is pivotal to understanding the robustness of the model against a diverse array of image corruptions.

 Ranked #1 on Cross-Modal Person Re-Identification on RegDB-C (mINP (Visible to Thermal) metric)

Cross-Modal Person Re-Identification Generalizable Person Re-identification

ContextNet: A Click-Through Rate Prediction Framework Using Contextual information to Refine Feature Embedding

3 code implementations26 Jul 2021 Zhiqiang Wang, Qingyun She, PengTao Zhang, Junlin Zhang

In this paper, We propose a novel CTR Framework named ContextNet that implicitly models high-order feature interactions by dynamically refining each feature's embedding according to the input context.

Click-Through Rate Prediction Recommendation Systems +1

Leaf-FM: A Learnable Feature Generation Factorization Machine for Click-Through Rate Prediction

no code implementations26 Jul 2021 Qingyun She, Zhiqiang Wang, Junlin Zhang

For example, the continuous features are usually transformed to the power forms by adding a new feature to allow it to easily form non-linear functions of the feature.

Click-Through Rate Prediction Feature Engineering +1

GLSD: The Global Large-Scale Ship Database and Baseline Evaluations

1 code implementation5 Jun 2021 Zhenfeng Shao, JiaMing Wang, Lianbing Deng, Xiao Huang, Tao Lu, Fang Luo, Ruiqian Zhang, Xianwei Lv, Chaoya Dang, Qing Ding, Zhiqiang Wang

In this paper, we introduce a challenging global large-scale ship database (called GLSD), designed specifically for ship detection tasks.

object-detection Object Detection

SSCAN: A Spatial-spectral Cross Attention Network for Hyperspectral Image Denoising

no code implementations23 May 2021 Zhiqiang Wang, Zhenfeng Shao, Xiao Huang, JiaMing Wang, Tao Lu, Sihang Zhang

In this study, we propose a novel HSI denoising network, termed SSCAN, that combines group convolutions and attention modules.

Hyperspectral Image Denoising Image Denoising

MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask

17 code implementations9 Feb 2021 Zhiqiang Wang, Qingyun She, Junlin Zhang

We also turn the feed-forward layer in DNN model into a mixture of addictive and multiplicative feature interactions by proposing MaskBlock in this paper.

Click-Through Rate Prediction Recommendation Systems

GateNet: Gating-Enhanced Deep Network for Click-Through Rate Prediction

4 code implementations6 Jul 2020 Tongwen Huang, Qingyun She, Zhiqiang Wang, Junlin Zhang

Inspired by these observations, we propose a novel model named GateNet which introduces either the feature embedding gate or the hidden gate to the embedding layer or hidden layers of DNN CTR models, respectively.

Click-Through Rate Prediction Recommendation Systems

Correct Normalization Matters: Understanding the Effect of Normalization On Deep Neural Network Models For Click-Through Rate Prediction

1 code implementation23 Jun 2020 Zhiqiang Wang, Qingyun She, PengTao Zhang, Junlin Zhang

Normalization has become one of the most fundamental components in many deep neural networks for machine learning tasks while deep neural network has also been widely used in CTR estimation field.

Click-Through Rate Prediction

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