Search Results for author: Zheng Lin

Found 64 papers, 30 papers with code

Slot Dependency Modeling for Zero-Shot Cross-Domain Dialogue State Tracking

no code implementations COLING 2022 Qingyue Wang, Yanan Cao, Piji Li, Yanhe Fu, Zheng Lin, Li Guo

Zero-shot learning for Dialogue State Tracking (DST) focuses on generalizing to an unseen domain without the expense of collecting in domain data.

Dialogue State Tracking Zero-Shot Learning

CLIO: Role-interactive Multi-event Head Attention Network for Document-level Event Extraction

no code implementations COLING 2022 Yubing Ren, Yanan Cao, Fang Fang, Ping Guo, Zheng Lin, Wei Ma, Yi Liu

Transforming the large amounts of unstructured text on the Internet into structured event knowledge is a critical, yet unsolved goal of NLP, especially when addressing document-level text.

Document-level Event Extraction Event Extraction

TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation

1 code implementation COLING 2022 Chenxu Yang, Zheng Lin, Jiangnan Li, Fandong Meng, Weiping Wang, Lanrui Wang, Jie zhou

The knowledge selector generally constructs a query based on the dialogue context and selects the most appropriate knowledge to help response generation.

Dialogue Generation Knowledge Distillation +1

Target Really Matters: Target-aware Contrastive Learning and Consistency Regularization for Few-shot Stance Detection

1 code implementation COLING 2022 Rui Liu, Zheng Lin, Huishan Ji, Jiangnan Li, Peng Fu, Weiping Wang

Despite the significant progress on this task, it is extremely time-consuming and budget-unfriendly to collect sufficient high-quality labeled data for every new target under fully-supervised learning, whereas unlabeled data can be collected easier.

Contrastive Learning Few-Shot Stance Detection

Multimodal Table Understanding

1 code implementation12 Jun 2024 Mingyu Zheng, Xinwei Feng, Qingyi Si, Qiaoqiao She, Zheng Lin, Wenbin Jiang, Weiping Wang

Although great progress has been made by previous table understanding methods including recent approaches based on large language models (LLMs), they rely heavily on the premise that given tables must be converted into a certain text sequence (such as Markdown or HTML) to serve as model input.

Language Modelling Large Language Model

Think out Loud: Emotion Deducing Explanation in Dialogues

no code implementations7 Jun 2024 Jiangnan Li, Zheng Lin, Lanrui Wang, Qingyi Si, Yanan Cao, Mo Yu, Peng Fu, Weiping Wang, Jie zhou

Besides, EDEN can help LLMs achieve better recognition of emotions and causes, which explores a new research direction of explainable emotion understanding in dialogues.

Common Sense Reasoning Emotion Cause Extraction

Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning

1 code implementation6 Jun 2024 Naibin Gu, Peng Fu, Xiyu Liu, Bowen Shen, Zheng Lin, Weiping Wang

The Light-PEFT framework allows for the simultaneous estimation of redundant parameters in both the foundation model and PEFT modules during the early stage of training.

Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization

no code implementations31 May 2024 Yisu Liu, Jinyang An, Wanqian Zhang, Dayan Wu, Jingzi Gu, Zheng Lin, Weiping Wang

In this paper, we propose DisDiff (Disrupting Diffusion), a novel adversarial attack method to disrupt the diffusion model outputs.

Adversarial Attack Image Generation

SATSense: Multi-Satellite Collaborative Framework for Spectrum Sensing

no code implementations24 May 2024 Haoxuan Yuan, Zhe Chen, Zheng Lin, Jinbo Peng, Zihan Fang, Yuhang Zhong, Zihang Song, Yue Gao

To address the above challenges, we first establish connections between the satellites by modeling their sensing data as a graph and devising a graph neural network-based algorithm to achieve effective spectrum sensing.

Contrastive Learning Data Compression +1

TrimCaching: Parameter-sharing AI Model Caching in Wireless Edge Networks

no code implementations7 May 2024 Guanqiao Qu, Zheng Lin, Fangming Liu, Xianhao Chen, Kaibin Huang

To this end, we formulate a parameter-sharing model placement problem to maximize the cache hit ratio in multi-edge wireless networks by balancing the fundamental tradeoff between storage efficiency and service latency.

Deep Learning Inference on Heterogeneous Mobile Processors: Potentials and Pitfalls

no code implementations3 May 2024 Sicong Liu, Wentao Zhou, Zimu Zhou, Bin Guo, Minfan Wang, Cheng Fang, Zheng Lin, Zhiwen Yu

There is a growing demand to deploy computation-intensive deep learning (DL) models on resource-constrained mobile devices for real-time intelligent applications.

IFViT: Interpretable Fixed-Length Representation for Fingerprint Matching via Vision Transformer

no code implementations12 Apr 2024 Yuhang Qiu, Honghui Chen, Xingbo Dong, Zheng Lin, Iman Yi Liao, Massimo Tistarelli, Zhe Jin

The first module, an interpretable dense registration module, establishes a Vision Transformer (ViT)-based Siamese Network to capture long-range dependencies and the global context in fingerprint pairs.

Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models

no code implementations9 Apr 2024 Zihan Fang, Zheng Lin, Zhe Chen, Xianhao Chen, Yue Gao, Yuguang Fang

Recently, there has been a surge in the development of advanced intelligent generative content (AIGC), especially large language models (LLMs).

Federated Learning Privacy Preserving

Minimize Quantization Output Error with Bias Compensation

1 code implementation2 Apr 2024 Cheng Gong, Haoshuai Zheng, Mengting Hu, Zheng Lin, Deng-Ping Fan, Yuzhi Zhang, Tao Li

Quantization is a promising method that reduces memory usage and computational intensity of Deep Neural Networks (DNNs), but it often leads to significant output error that hinder model deployment.


FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data

no code implementations25 Mar 2024 Yuxin Zhang, Haoyu Chen, Zheng Lin, Zhe Chen, Jin Zhao

Clustered federated learning (CFL) is proposed to mitigate the performance deterioration stemming from data heterogeneity in federated learning (FL) by grouping similar clients for cluster-wise model training.

Dimensionality Reduction Federated Learning

AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks

no code implementations19 Mar 2024 Zheng Lin, Guanqiao Qu, Wei Wei, Xianhao Chen, Kin K. Leung

In this paper, we provide a convergence analysis of SFL which quantifies the impact of model splitting (MS) and client-side model aggregation (MA) on the learning performance, serving as a theoretical foundation.

Edge-computing Federated Learning

Previously on the Stories: Recap Snippet Identification for Story Reading

no code implementations11 Feb 2024 Jiangnan Li, Qiujing Wang, Liyan Xu, Wenjie Pang, Mo Yu, Zheng Lin, Weiping Wang, Jie zhou

Similar to the "previously-on" scenes in TV shows, recaps can help book reading by recalling the readers' memory about the important elements in previous texts to better understand the ongoing plot.

Are Large Language Models Table-based Fact-Checkers?

no code implementations4 Feb 2024 Hangwen Zhang, Qingyi Si, Peng Fu, Zheng Lin, Weiping Wang

Finally, we analyze some possible directions to promote the accuracy of TFV via LLMs, which is beneficial to further research of table reasoning.

Fact Verification In-Context Learning +2

A Pedestrian is Worth One Prompt: Towards Language Guidance Person Re-Identification

no code implementations CVPR 2024 Zexian Yang, Dayan Wu, Chenming Wu, Zheng Lin, Jingzi Gu, Weiping Wang

Whiteness the impressive capabilities in multimodal understanding of Vision Language Foundation Model CLIP a recent two-stage CLIP-based method employs automated prompt engineering to obtain specific textual labels for classifying pedestrians.

Attribute Person Re-Identification +1

Object Attribute Matters in Visual Question Answering

no code implementations20 Dec 2023 Peize Li, Qingyi Si, Peng Fu, Zheng Lin, Yan Wang

In this paper, we propose a novel VQA approach from the perspective of utilizing object attribute, aiming to achieve better object-level visual-language alignment and multimodal scene understanding.

Attribute Graph Neural Network +6

TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes

no code implementations CVPR 2024 Xuying Zhang, Bo-Wen Yin, Yuming Chen, Zheng Lin, Yunheng Li, Qibin Hou, Ming-Ming Cheng

Particularly, a cross-modal graph is constructed to align the object points accurately and noun phrases decoupled from the 3D mesh and textual description.

Graph Attention Object

Sibyl: Sensible Empathetic Dialogue Generation with Visionary Commonsense Knowledge

no code implementations26 Nov 2023 Lanrui Wang, Jiangnan Li, Chenxu Yang, Zheng Lin, Hongyin Tang, Huan Liu, Xiaolei Huang, Yanan Cao, Jingang Wang, Weiping Wang

Recently, there has been a heightened interest in building chatbots based on Large Language Models (LLMs) to emulate human-like qualities in dialogues, including expressing empathy and offering emotional support.

Dialogue Generation

FedSN: A Novel Federated Learning Framework over LEO Satellite Networks

no code implementations2 Nov 2023 Zheng Lin, Zhe Chen, Zihan Fang, Xianhao Chen, Xiong Wang, Yue Gao

To this end, we propose FedSN as a general FL framework to tackle the above challenges, and fully explore data diversity on LEO satellites.

Federated Learning Image Classification +1

Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation

no code implementations13 Oct 2023 Chenxu Yang, Zheng Lin, Lanrui Wang, Chong Tian, Liang Pang, Jiangnan Li, Qirong Ho, Yanan Cao, Weiping Wang

Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context.

Contrastive Learning Dialogue Generation

An Empirical Study of Instruction-tuning Large Language Models in Chinese

1 code implementation11 Oct 2023 Qingyi Si, Tong Wang, Zheng Lin, Xu Zhang, Yanan Cao, Weiping Wang

This paper will release a powerful Chinese LLMs that is comparable to ChatGLM.

Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities

no code implementations28 Sep 2023 Zheng Lin, Guanqiao Qu, Qiyuan Chen, Xianhao Chen, Zhe Chen, Kaibin Huang

In both aspects, considering the inherent resource limitations at the edge, we discuss various cutting-edge techniques, including split learning/inference, parameter-efficient fine-tuning, quantization, and parameter-sharing inference, to facilitate the efficient deployment of LLMs.

Edge-computing Quantization

Optimal Resource Allocation for U-Shaped Parallel Split Learning

no code implementations17 Aug 2023 Song Lyu, Zheng Lin, Guanqiao Qu, Xianhao Chen, Xiaoxia Huang, Pan Li

In this paper, we develop a novel parallel U-shaped split learning and devise the optimal resource optimization scheme to improve the performance of edge networks.

Split Learning in 6G Edge Networks

no code implementations21 Jun 2023 Zheng Lin, Guanqiao Qu, Xianhao Chen, Kaibin Huang

With the proliferation of distributed edge computing resources, the 6G mobile network will evolve into a network for connected intelligence.

Edge-computing Federated Learning +1

Referring Camouflaged Object Detection

1 code implementation13 Jun 2023 Xuying Zhang, Bowen Yin, Zheng Lin, Qibin Hou, Deng-Ping Fan, Ming-Ming Cheng

We consider the problem of referring camouflaged object detection (Ref-COD), a new task that aims to segment specified camouflaged objects based on a small set of referring images with salient target objects.

Object object-detection +1

Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking

no code implementations1 Jun 2023 Qingyue Wang, Liang Ding, Yanan Cao, Yibing Zhan, Zheng Lin, Shi Wang, DaCheng Tao, Li Guo

Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of task-oriented dialogue domains without the cost of collecting in-domain data.

Dialogue State Tracking Transfer Learning

Combo of Thinking and Observing for Outside-Knowledge VQA

1 code implementation10 May 2023 Qingyi Si, Yuchen Mo, Zheng Lin, Huishan Ji, Weiping Wang

Some existing solutions draw external knowledge into the cross-modality space which overlooks the much vaster textual knowledge in natural-language space, while others transform the image into a text that further fuses with the textual knowledge into the natural-language space and completely abandons the use of visual features.

Decoder Question Answering +2

Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks

no code implementations26 Mar 2023 Zheng Lin, Guangyu Zhu, Yiqin Deng, Xianhao Chen, Yue Gao, Kaibin Huang, Yuguang Fang

The increasingly deeper neural networks hinder the democratization of privacy-enhancing distributed learning, such as federated learning (FL), to resource-constrained devices.

Edge-computing Federated Learning +1

Co-Salient Object Detection with Co-Representation Purification

1 code implementation14 Mar 2023 Ziyue Zhu, Zhao Zhang, Zheng Lin, Xing Sun, Ming-Ming Cheng

Such irrelevant information in the co-representation interferes with its locating of co-salient objects.

Co-Salient Object Detection Object +2

COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models

1 code implementation27 Oct 2022 Bowen Shen, Zheng Lin, Yuanxin Liu, Zhengxiao Liu, Lei Wang, Weiping Wang

Motivated by such considerations, we propose a collaborative optimization for PLMs that integrates static model compression and dynamic inference acceleration.

Model Compression

Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering

1 code implementation26 Oct 2022 Qingyi Si, Yuanxin Liu, Zheng Lin, Peng Fu, Weiping Wang

To this end, we systematically study the design of a training and compression pipeline to search the subnetworks, as well as the assignment of sparsity to different modality-specific modules.

Question Answering Visual Question Answering

Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension

no code implementations26 Oct 2022 Jiangnan Li, Mo Yu, Fandong Meng, Zheng Lin, Peng Fu, Weiping Wang, Jie zhou

Although these tasks are effective, there are still urging problems: (1) randomly masking speakers regardless of the question cannot map the speaker mentioned in the question to the corresponding speaker in the dialogue, and ignores the speaker-centric nature of utterances.

Reading Comprehension

Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection

1 code implementation21 Oct 2022 Lanrui Wang, Jiangnan Li, Zheng Lin, Fandong Meng, Chenxu Yang, Weiping Wang, Jie zhou

We use a fine-grained encoding strategy which is more sensitive to the emotion dynamics (emotion flow) in the conversations to predict the emotion-intent characteristic of response.

Dialogue Generation Emotion Recognition +2

A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models

1 code implementation11 Oct 2022 Yuanxin Liu, Fandong Meng, Zheng Lin, Jiangnan Li, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou

In response to the efficiency problem, recent studies show that dense PLMs can be replaced with sparse subnetworks without hurting the performance.

Natural Language Understanding

Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA

1 code implementation10 Oct 2022 Qingyi Si, Fandong Meng, Mingyu Zheng, Zheng Lin, Yuanxin Liu, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou

To overcome this limitation, we propose a new dataset that considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.

Question Answering Visual Question Answering

Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning

1 code implementation10 Oct 2022 Qingyi Si, Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou

However, these models reveal a trade-off that the improvements on OOD data severely sacrifice the performance on the in-distribution (ID) data (which is dominated by the biased samples).

Contrastive Learning Question Answering +1

Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization

no code implementations ACL 2022 Ruipeng Jia, Xingxing Zhang, Yanan Cao, Shi Wang, Zheng Lin, Furu Wei

In zero-shot multilingual extractive text summarization, a model is typically trained on English summarization dataset and then applied on summarization datasets of other languages.

Extractive Summarization Extractive Text Summarization +1

Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training

1 code implementation NAACL 2022 Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou

Firstly, we discover that the success of magnitude pruning can be attributed to the preserved pre-training performance, which correlates with the downstream transferability.

Transfer Learning

Image Harmonization by Matching Regional References

no code implementations10 Apr 2022 Ziyue Zhu, Zhao Zhang, Zheng Lin, Ruiqi Wu, Zhi Chai, Chun-Le Guo

To achieve visual consistency in composite images, recent image harmonization methods typically summarize the appearance pattern of global background and apply it to the global foreground without location discrepancy.

Image Harmonization

Interactive Style Transfer: All is Your Palette

no code implementations25 Mar 2022 Zheng Lin, Zhao Zhang, Kang-Rui Zhang, Bo Ren, Ming-Ming Cheng

Our IST method can serve as a brush, dip style from anywhere, and then paint to any region of the target content image.

Style Transfer

Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation

1 code implementation ACL 2021 Yuanxin Liu, Fandong Meng, Zheng Lin, Weiping Wang, Jie zhou

In this paper, however, we observe that although distilling the teacher's hidden state knowledge (HSK) is helpful, the performance gain (marginal utility) diminishes quickly as more HSK is distilled.

Knowledge Distillation

Check It Again: Progressive Visual Question Answering via Visual Entailment

1 code implementation8 Jun 2021 Qingyi Si, Zheng Lin, Mingyu Zheng, Peng Fu, Weiping Wang

Besides, they only explore the interaction between image and question, ignoring the semantics of candidate answers.

Question Answering Visual Entailment +1

ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques

1 code implementation21 Mar 2021 Yuanxin Liu, Zheng Lin, Fengcheng Yuan

Based on the empirical findings, our best compressed model, dubbed Refined BERT cOmpreSsion with InTegrAted techniques (ROSITA), is $7. 5 \times$ smaller than BERT while maintains $98. 5\%$ of the performance on five tasks of the GLUE benchmark, outperforming the previous BERT compression methods with similar parameter budget.

Knowledge Distillation

A Hierarchical Transformer with Speaker Modeling for Emotion Recognition in Conversation

1 code implementation29 Dec 2020 Jiangnan Li, Zheng Lin, Peng Fu, Qingyi Si, Weiping Wang

It can be regarded as a personalized and interactive emotion recognition task, which is supposed to consider not only the semantic information of text but also the influences from speakers.

Emotion Recognition in Conversation

Learning Class-Transductive Intent Representations for Zero-shot Intent Detection

1 code implementation3 Dec 2020 Qingyi Si, Yuanxin Liu, Peng Fu, Zheng Lin, Jiangnan Li, Weiping Wang

A critical problem behind these limitations is that the representations of unseen intents cannot be learned in the training stage.

Intent Detection Multi-Task Learning +1

Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection

no code implementations Findings of the Association for Computational Linguistics 2020 Hongliang Pan, Zheng Lin, Peng Fu, Yatao Qi, Weiping Wang

Inspired by this, we propose a BERT architecture-based model, which concentrates on both intra and inter-modality incongruity for multi-modal sarcasm detection.

Sarcasm Detection

Re-thinking Co-Salient Object Detection

2 code implementations7 Jul 2020 Deng-Ping Fan, Tengpeng Li, Zheng Lin, Ge-Peng Ji, Dingwen Zhang, Ming-Ming Cheng, Huazhu Fu, Jianbing Shen

CoSOD is an emerging and rapidly growing extension of salient object detection (SOD), which aims to detect the co-occurring salient objects in a group of images.

Benchmarking Co-Salient Object Detection +3

Interactive Image Segmentation With First Click Attention

2 code implementations CVPR 2020 Zheng Lin, Zhao Zhang, Lin-Zhuo Chen, Ming-Ming Cheng, Shao-Ping Lu

In the task of interactive image segmentation, users initially click one point to segment the main body of the target object and then provide more points on mislabeled regions iteratively for a precise segmentation.

Image Segmentation Interactive Segmentation +2

Bilateral Attention Network for RGB-D Salient Object Detection

1 code implementation30 Apr 2020 Zhao Zhang, Zheng Lin, Jun Xu, Wenda Jin, Shao-Ping Lu, Deng-Ping Fan

To better explore salient information in both foreground and background regions, this paper proposes a Bilateral Attention Network (BiANet) for the RGB-D SOD task.

Object object-detection +3

Keyphrase Prediction With Pre-trained Language Model

no code implementations22 Apr 2020 Rui Liu, Zheng Lin, Weiping Wang

Considering the different characteristics of extractive and generative methods, we propose to divide the keyphrase prediction into two subtasks, i. e., present keyphrase extraction (PKE) and absent keyphrase generation (AKG), to fully exploit their respective advantages.

Keyphrase Extraction Keyphrase Generation +1

Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation

1 code implementation9 Apr 2020 Lin-Zhuo Chen, Zheng Lin, Ziqin Wang, Yong-Liang Yang, Ming-Ming Cheng

S-Conv is competent to infer the sampling offset of the convolution kernel guided by the 3D spatial information, helping the convolutional layer adjust the receptive field and adapt to geometric transformations.

Ranked #23 on Semantic Segmentation on SUN-RGBD (using extra training data)

RGBD Semantic Segmentation Segmentation +1

Unsupervised Pre-training for Natural Language Generation: A Literature Review

no code implementations13 Nov 2019 Yuanxin Liu, Zheng Lin

They are classified into architecture-based methods and strategy-based methods, based on their way of handling the above obstacle.

Natural Language Understanding Text Generation +1

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