Gang Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Gang Zhao has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Guanting Dong
Renmin University of China, Beijing, China
2 shared publications - Si Li
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications - Weiran Xu
Beijing University of Posts and Telecommunications
2 shared publications - Bin Duan
Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Binghao Tang
Meituan, Beijing, China
1 shared publication - Bo Zheng
Alibaba Group, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 631-640
Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 631-640
Open AccessExplainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4183-4187
CAG: A Consistency-Adaptive Text-Image Alignment Generation for Joint Multimodal Entity-Relation Extraction
Joint Multimodal Entity-Relation Extraction (JMERE) aims to extract entity-relationship triples in texts from given image-text pairs. As a joint multimodal information extraction task, it has attracted increasing research interest. Previous works of JMERE typically utilize graph networks to align textual entities and visual objects and achieve promising performance. However, these methods do not pay attention to the inconsistency between text and image and the straight alignment could limit the performance of JMERE models. In this paper, we propose a Consistency-adaptive text-image Alignment Generation (CAG) framework for various text-image consistency scenarios. Specifically, we propose a Consistency Factor (CF) to measure the consistency between images and texts. We also design consistency-adaptive contrastive learning based on CF, which can reduce the impact of inconsistent visual and textual information. Additionally, we adopt JMERE-specifical instruction tuning for better entity-relationship triplet generation. Experimental results on the JMERE dataset demonstrate that our proposed CAG is effective and achieves state-of-the-art performance.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4183-4187
Open AccessCAG: A Consistency-Adaptive Text-Image Alignment Generation for Joint Multimodal Entity-Relation Extraction
Joint Multimodal Entity-Relation Extraction (JMERE) aims to extract entity-relationship triples in texts from given image-text pairs. As a joint multimodal information extraction task, it has attracted increasing research interest. Previous works of JMERE typically utilize graph networks to align textual entities and visual objects and achieve promising performance. However, these methods do not pay attention to the inconsistency between text and image and the straight alignment could limit the performance of JMERE models. In this paper, we propose a Consistency-adaptive text-image Alignment Generation (CAG) framework for various text-image consistency scenarios. Specifically, we propose a Consistency Factor (CF) to measure the consistency between images and texts. We also design consistency-adaptive contrastive learning based on CF, which can reduce the impact of inconsistent visual and textual information. Additionally, we adopt JMERE-specifical instruction tuning for better entity-relationship triplet generation. Experimental results on the JMERE dataset demonstrate that our proposed CAG is effective and achieves state-of-the-art performance.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 430-440
A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER
The objective of few-shot named entity recognition is to identify named entities with limited labeled instances. Previous works have primarily focused on optimizing the traditional token-wise classification framework, while neglecting the exploration of information based on NER data characteristics. To address this issue, we propose a Multi-Task Semantic Decomposition Framework via Joint Task-specific Pre-training (MSDP) for few-shot NER. Drawing inspiration from demonstration-based and contrastive learning, we introduce two novel pre-training tasks: Demonstration-based Masked Language Modeling (MLM) and Class Contrastive Discrimination. These tasks effectively incorporate entity boundary information and enhance entity representation in Pre-trained Language Models (PLMs). In the downstream main task, we introduce a multi-task joint optimization framework with the semantic decomposing method, which facilitates the model to integrate two different semantic information for entity classification. Experimental results of two few-shot NER benchmarks demonstrate that MSDP consistently outperforms strong baselines by a large margin. Extensive analyses validate the effectiveness and generalization of MSDP.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 430-440
Open AccessA Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER
The objective of few-shot named entity recognition is to identify named entities with limited labeled instances. Previous works have primarily focused on optimizing the traditional token-wise classification framework, while neglecting the exploration of information based on NER data characteristics. To address this issue, we propose a Multi-Task Semantic Decomposition Framework via Joint Task-specific Pre-training (MSDP) for few-shot NER. Drawing inspiration from demonstration-based and contrastive learning, we introduce two novel pre-training tasks: Demonstration-based Masked Language Modeling (MLM) and Class Contrastive Discrimination. These tasks effectively incorporate entity boundary information and enhance entity representation in Pre-trained Language Models (PLMs). In the downstream main task, we introduce a multi-task joint optimization framework with the semantic decomposing method, which facilitates the model to integrate two different semantic information for entity classification. Experimental results of two few-shot NER benchmarks demonstrate that MSDP consistently outperforms strong baselines by a large margin. Extensive analyses validate the effectiveness and generalization of MSDP.
- 23 April 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 248
Explainable document-level event extraction via back-tracing to sentence-level event clues
- 23 April 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 248
Explainable document-level event extraction via back-tracing to sentence-level event clues
- Open Access
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 6345-6350
Entity-level Interaction via Heterogeneous Graph for Multimodal Named Entity Recognition
Gang Zhao, Guanting Dong, Yidong Shi, Haolong Yan, Weiran Xu, Si Li. Findings of the Association for Computational Linguistics: EMNLP 2022. 2022.
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 6345-6350
Open AccessEntity-level Interaction via Heterogeneous Graph for Multimodal Named Entity Recognition
Gang Zhao, Guanting Dong, Yidong Shi, Haolong Yan, Weiran Xu, Si Li. Findings of the Association for Computational Linguistics: EMNLP 2022. 2022.
- 1 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2095-2099
Experimental Evaluation of Metaheuristic Optimization of Gradients as an Alternative to Backpropagation
In this paper, we continue our research on the previously proposed “favorable gradients”, the gradients selected by random search that are beneficial for training of DNNs. The contribution of this study can be stated as follows: we experimentally analyze two methods of calculating gradients - backpropagation and favorable gradients optimization - and we show that the gradients can be optimized by metaheuristic optimization techniques such as evolution strategies and further used for training DNNs with a selected optimizer. Thus, the proposed method can be viewed as an alternative to backpropagation, since it is theoretically possible to train DNNs end-to-end by using only favorable gradients. However, in practice this method turns out to be considerably slower than backpropagation, therefore a combination of these two techniques has been examined.
- 1 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2095-2099
Experimental Evaluation of Metaheuristic Optimization of Gradients as an Alternative to Backpropagation
In this paper, we continue our research on the previously proposed “favorable gradients”, the gradients selected by random search that are beneficial for training of DNNs. The contribution of this study can be stated as follows: we experimentally analyze two methods of calculating gradients - backpropagation and favorable gradients optimization - and we show that the gradients can be optimized by metaheuristic optimization techniques such as evolution strategies and further used for training DNNs with a selected optimizer. Thus, the proposed method can be viewed as an alternative to backpropagation, since it is theoretically possible to train DNNs end-to-end by using only favorable gradients. However, in practice this method turns out to be considerably slower than backpropagation, therefore a combination of these two techniques has been examined.
- 4 May 2016
- Published by Wiley in Computer Animation and Virtual Worlds
- Vol. 27 (3-4) , 231-240
An efficient GPU out‐of‐core framework for interactive rendering of large‐scale CAD models
Real‐time rendering of large‐scale engineering computer‐aided design (CAD) models has been recognized as a challenging task. Because of the constraints of limited graphics processing unit (GPU) memory size and computation capacity, a massive model with hundreds of millions of triangles cannot be loaded and rendered in real‐time using most of modern GPUs. In this paper, an efficient GPU out‐of‐core framework is proposed for interactively visualizing large‐scale CAD models. To improve efficiency of data fetching from CPU host memory to GPU device memory, a parallel offline geometry compression scheme is introduced to minimize the storage cost of each primitive by compressing the levels of detail (LOD) geometries into a highly compact format. At the rendering stage, occlusion culling and LOD processing algorithms are integrated and implemented with an efficient GPU‐based approach to determine a minimal scale of primitives to be transferred for each frame. A prototype software system is developed to preprocess and render massive CAD models with the proposed framework. Experimental results show that users can walkthrough massive CAD models with hundreds of millions of triangles at high frame rates using our framework. Copyright © 2016 John Wiley & Sons, Ltd.
- 4 May 2016
- Published by Wiley in Computer Animation and Virtual Worlds
- Vol. 27 (3-4) , 231-240
An efficient GPU out‐of‐core framework for interactive rendering of large‐scale CAD models
Real‐time rendering of large‐scale engineering computer‐aided design (CAD) models has been recognized as a challenging task. Because of the constraints of limited graphics processing unit (GPU) memory size and computation capacity, a massive model with hundreds of millions of triangles cannot be loaded and rendered in real‐time using most of modern GPUs. In this paper, an efficient GPU out‐of‐core framework is proposed for interactively visualizing large‐scale CAD models. To improve efficiency of data fetching from CPU host memory to GPU device memory, a parallel offline geometry compression scheme is introduced to minimize the storage cost of each primitive by compressing the levels of detail (LOD) geometries into a highly compact format. At the rendering stage, occlusion culling and LOD processing algorithms are integrated and implemented with an efficient GPU‐based approach to determine a minimal scale of primitives to be transferred for each frame. A prototype software system is developed to preprocess and render massive CAD models with the proposed framework. Experimental results show that users can walkthrough massive CAD models with hundreds of millions of triangles at high frame rates using our framework. Copyright © 2016 John Wiley & Sons, Ltd.
- Open Access
- 1 January 2004
- Published by U-turn Press LLC in Computer-Aided Design and Applications
- Vol. 1 (1-4) , 727-732
A Heuristic Knot Placement Algorithm for B-Spline Curve Approximation
Computer-Aided Design and Applications is an international journal on the applications of CAD and CAM. It publishes papers in the general domain of CAD plus in emerging fields like bio-CAD, nano-CAD, soft-CAD, garment-CAD, PLM, PDM, CAD data mining, CAD and the internet, CAD education, genetic algorithms and CAD engines. The journal is aimed at all developers and users of CAD technology to ptovide CAD solutions for various stages of design and manufacturing. The journal publishes all about Computer-Aided Design and Computer-Aided technologies.
- 1 January 2004
- Published by U-turn Press LLC in Computer-Aided Design and Applications
- Vol. 1 (1-4) , 727-732
Open AccessA Heuristic Knot Placement Algorithm for B-Spline Curve Approximation
Computer-Aided Design and Applications is an international journal on the applications of CAD and CAM. It publishes papers in the general domain of CAD plus in emerging fields like bio-CAD, nano-CAD, soft-CAD, garment-CAD, PLM, PDM, CAD data mining, CAD and the internet, CAD education, genetic algorithms and CAD engines. The journal is aimed at all developers and users of CAD technology to ptovide CAD solutions for various stages of design and manufacturing. The journal publishes all about Computer-Aided Design and Computer-Aided technologies.