Search Results for author: Yin Zhang

Found 67 papers, 24 papers with code

Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition

1 code implementation EMNLP 2020 Xiangji Zeng, Yunliang Li, Yuchen Zhai, Yin Zhang

In this paper, we decompose the sentence into two parts: entity and context, and rethink the relationship between them and model performance from a causal perspective.

counterfactual named-entity-recognition +3

UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings

no code implementations Findings (EMNLP) 2021 Zhi Li, Yuchen Zhai, Chengyu Wang, Minghui Qiu, Kailiang Li, Yin Zhang

Inspired by the fact that words with similar semantic can share a part of weights, we divide the embeddings of words into two parts: unique embedding and class embedding.

Language Modelling Semantic Similarity +2

Meta Distant Transfer Learning for Pre-trained Language Models

no code implementations EMNLP 2021 Chengyu Wang, Haojie Pan, Minghui Qiu, Jun Huang, Fei Yang, Yin Zhang

For tasks related to distant domains with different class label sets, PLMs may memorize non-transferable knowledge for the target domain and suffer from negative transfer.

Implicit Relations Meta-Learning +2

Domain Adaptive Detection of MAVs: A Benchmark and Noise Suppression Network

1 code implementation25 Mar 2024 Yin Zhang, Jinhong Deng, Peidong Liu, Wen Li, Shiyu Zhao

A new benchmark for cross-domain MAV detection is proposed based on the proposed dataset.

Pseudo Label

Global-Local MAV Detection under Challenging Conditions based on Appearance and Motion

1 code implementation18 Dec 2023 Hanqing Guo, Ye Zheng, Yin Zhang, Zhi Gao, Shiyu Zhao

In this paper, we propose a global-local MAV detector that can fuse both motion and appearance features for MAV detection under challenging conditions.

Computational Efficiency

Mixed Distillation Helps Smaller Language Model Better Reasoning

no code implementations17 Dec 2023 Chenglin Li, Qianglong Chen, Liangyue Li, Caiyu Wang, Yicheng Li, Zulong Chen, Yin Zhang

While large language models (LLMs) have demonstrated exceptional performance in recent natural language processing (NLP) tasks, their deployment poses substantial challenges due to high computational and memory demands in real-world applications.

Knowledge Distillation Language Modelling

Why "classic" Transformers are shallow and how to make them go deep

no code implementations11 Dec 2023 Yueyao Yu, Yin Zhang

Since its introduction in 2017, Transformer has emerged as the leading neural network architecture, catalyzing revolutionary advancements in many AI disciplines.

HierarchicalContrast: A Coarse-to-Fine Contrastive Learning Framework for Cross-Domain Zero-Shot Slot Filling

1 code implementation13 Oct 2023 Junwen Zhang, Yin Zhang

To alleviate this issue, we present a novel Hierarchical Contrastive Learning Framework (HiCL) for zero-shot slot filling.

Contrastive Learning slot-filling +2

Large Language Models Are Also Good Prototypical Commonsense Reasoners

no code implementations22 Sep 2023 Chenin Li, Qianglong Chen, Yin Zhang, Yifei Zhang, Hongxiang Yao

Commonsense reasoning is a pivotal skill for large language models, yet it presents persistent challenges in specific tasks requiring this competence.

StrategyQA

Crucial Feature Capture and Discrimination for Limited Training Data SAR ATR

1 code implementation20 Aug 2023 Chenwei Wang, Siyi Luo, Jifang Pei, Yulin Huang, Yin Zhang, Jianyu Yang

Based on the initial recognition results, the feature capture module automatically searches and locks the crucial image regions for correct recognition, which we named as the golden key of image.

SAR ATR Method with Limited Training Data via an Embedded Feature Augmenter and Dynamic Hierarchical-Feature Refiner

no code implementations20 Aug 2023 Chenwei Wang, Siyi Luo, Yulin Huang, Jifang Pei, Yin Zhang, Jianyu Yang

The designed augmenter increases the amount of information available for supervised training and improves the separability of the extracted features.

SAR Ship Target Recognition Via Multi-Scale Feature Attention and Adaptive-Weighed Classifier

no code implementations20 Aug 2023 Chenwei Wang, Jifang Pei, Siyi Luo, Weibo Huo, Yulin Huang, Yin Zhang, Jianyu Yang

Therefore, we proposed a SAR ship recognition method via multi-scale feature attention and adaptive-weighted classifier to enhance features in each scale, and adaptively choose the effective feature scale for accurate recognition.

SAR Ship Target Recognition via Selective Feature Discrimination and Multifeature Center Classifier

no code implementations20 Aug 2023 Chenwei Wang, Siyi Luo, Jifang Pei, Yulin Huang, Yin Zhang, Jianyu Yang

However, the characteristics of SAR ship images, large inner-class variance, and small interclass difference lead to the whole features containing useless partial features and a single feature center for each class in the classifier failing with large inner-class variance.

An Entropy-Awareness Meta-Learning Method for SAR Open-Set ATR

no code implementations20 Aug 2023 Chenwei Wang, Siyi Luo, Jifang Pei, Xiaoyu Liu, Yulin Huang, Yin Zhang, Jianyu Yang

In this letter, we propose an entropy-awareness meta-learning method that improves the exclusiveness of feature distribution of known classes which means our method is effective for not only classifying the seen classes but also encountering the unseen other classes.

Meta-Learning Open Set Learning

Causal SAR ATR with Limited Data via Dual Invariance

1 code implementation18 Aug 2023 Chenwei Wang, You Qin, Li Li, Siyi Luo, Yulin Huang, Jifang Pei, Yin Zhang, Jianyu Yang

As a result, it has a detrimental causal effect damaging the efficacy of feature $X$ extracted from SAR images, leading to weak generalization of SAR ATR with limited data.

SAR Target Image Generation Method Using Azimuth-Controllable Generative Adversarial Network

no code implementations10 Aug 2023 Chenwei Wang, Jifang Pei, Xiaoyu Liu, Yulin Huang, Deqing Mao, Yin Zhang, Jianyu Yang

The similarity discriminator can differentiate the generated SAR target images from the real SAR images to ensure the accuracy of the generated, while the azimuth predictor measures the difference of azimuth between the generated and the desired to ensure the azimuth controllability of the generated.

Generative Adversarial Network Image Generation

Global in Local: A Convolutional Transformer for SAR ATR FSL

no code implementations10 Aug 2023 Chenwei Wang, Yulin Huang, Xiaoyu Liu, Jifang Pei, Yin Zhang, Jianyu Yang

Convolutional neural networks (CNNs) have dominated the synthetic aperture radar (SAR) automatic target recognition (ATR) for years.

Few-Shot Learning

SAR ATR under Limited Training Data Via MobileNetV3

1 code implementation27 Jun 2023 Chenwei Wang, Siyi Luo, Lin Liu, Yin Zhang, Jifang Pei, Yulin Huang, Jianyu Yang

In recent years, deep learning has been widely used to solve the bottleneck problem of synthetic aperture radar (SAR) automatic target recognition (ATR).

Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering

2 code implementations1 Jun 2023 Wenjin Wang, Yunhao Li, Yixin Ou, Yin Zhang

Instead, in this paper, we find that instruction-tuning language models like Claude and ChatGPT can understand layout by spaces and line breaks.

Optical Character Recognition (OCR) Question Answering +2

WYWEB: A NLP Evaluation Benchmark For Classical Chinese

1 code implementation23 May 2023 Bo Zhou, Qianglong Chen, Tianyu Wang, Xiaomi Zhong, Yin Zhang

To fully evaluate the overall performance of different NLP models in a given domain, many evaluation benchmarks are proposed, such as GLUE, SuperGLUE and CLUE.

Machine Translation Natural Language Understanding +2

Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering

no code implementations14 May 2023 Qianglong Chen, Guohai Xu, Ming Yan, Ji Zhang, Fei Huang, Luo Si, Yin Zhang

Existing knowledge-enhanced methods have achieved remarkable results in certain QA tasks via obtaining diverse knowledge from different knowledge bases.

Explanation Generation Question Answering

AMTSS: An Adaptive Multi-Teacher Single-Student Knowledge Distillation Framework For Multilingual Language Inference

no code implementations13 May 2023 Qianglong Chen, Feng Ji, Feng-Lin Li, Guohai Xu, Ming Yan, Ji Zhang, Yin Zhang

To support cost-effective language inference in multilingual settings, we propose AMTSS, an adaptive multi-teacher single-student distillation framework, which allows distilling knowledge from multiple teachers to a single student.

Knowledge Distillation

Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning

1 code implementation CVPR 2023 Wenjin Wang, Yunqing Hu, Qianglong Chen, Yin Zhang

In this paper, we propose the Parameter Allocation & Regularization (PAR), which adaptively select an appropriate strategy for each task from parameter allocation and regularization based on its learning difficulty.

OTSeq2Set: An Optimal Transport Enhanced Sequence-to-Set Model for Extreme Multi-label Text Classification

1 code implementation26 Oct 2022 Jie Cao, Yin Zhang

However, such models can't predict a relatively complete and variable-length label subset for each document, because they select positive labels relevant to the document by a fixed threshold or take top k labels in descending order of scores.

Multi Label Text Classification Multi-Label Text Classification +1

Empowering Long-tail Item Recommendation through Cross Decoupling Network (CDN)

no code implementations25 Oct 2022 Yin Zhang, Ruoxi Wang, Tiansheng Yao, Xinyang Yi, Lichan Hong, James Caverlee, Ed H. Chi, Derek Zhiyuan Cheng

In this work, we aim to improve tail item recommendations while maintaining the overall performance with less training and serving cost.

Memorization Recommendation Systems +1

ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding

no code implementations18 Sep 2022 Wenjin Wang, Zhengjie Huang, Bin Luo, Qianglong Chen, Qiming Peng, Yinxu Pan, Weichong Yin, Shikun Feng, Yu Sun, dianhai yu, Yin Zhang

At first, a document graph is proposed to model complex relationships among multi-grained multimodal elements, in which salient visual regions are detected by a cluster-based method.

Common Sense Reasoning document understanding +1

LFGCF: Light Folksonomy Graph Collaborative Filtering for Tag-Aware Recommendation

no code implementations6 Aug 2022 Yin Zhang, Can Xu, XianJun Wu, Yan Zhang, LiGang Dong, Weigang Wang

Recently, many efforts have been devoted to improving Tag-aware recommendation systems (TRS) with Graph Convolutional Networks (GCN), which has become new state-of-the-art for the general recommendation.

Collaborative Filtering Recommendation Systems +1

DictBERT: Dictionary Description Knowledge Enhanced Language Model Pre-training via Contrastive Learning

no code implementations1 Aug 2022 Qianglong Chen, Feng-Lin Li, Guohai Xu, Ming Yan, Ji Zhang, Yin Zhang

We evaluate our approach on a variety of knowledge driven and language understanding tasks, including NER, relation extraction, CommonsenseQA, OpenBookQA and GLUE.

Contrastive Learning Language Modelling +2

POViT: Vision Transformer for Multi-objective Design and Characterization of Nanophotonic Devices

no code implementations17 May 2022 Xinyu Chen, Renjie Li, Yueyao Yu, Yuanwen Shen, Wenye Li, Zhaoyu Zhang, Yin Zhang

In this work, we propose the first-ever Transformer model (POViT) to efficiently design and simulate semiconductor photonic devices with multiple objectives.

Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition

no code implementations22 Apr 2022 Yunqing Hu, Xuan Jin, Yin Zhang, Haiwen Hong, Jingfeng Zhang, Feihu Yan, Yuan He, Hui Xue

Finally, we propose a weakly supervised object localization-based approach to extract multi-scale local features, to form a multi-view pipeline.

Weakly-Supervised Object Localization

Variability of Neural Networks and Han-Layer: A Variability-Inspired Model

no code implementations29 Sep 2021 Yueyao Yu, Yin Zhang

We introduce a notion of variability to view such issues under the setting of a fixed number of parameters which is, in general, a dominant cost-factor.

Similar Scenes arouse Similar Emotions: Parallel Data Augmentation for Stylized Image Captioning

no code implementations26 Aug 2021 Guodun Li, Yuchen Zhai, Zehao Lin, Yin Zhang

Second, we construct the plugable multi-modal scene retriever to retrieve scenes represented with pairs of an image and its stylized caption, which are similar to the query image or caption in the large-scale factual data.

Data Augmentation Image Captioning +1

KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference

no code implementations ACL 2021 Qianglong Chen, Feng Ji, Xiangji Zeng, Feng-Lin Li, Ji Zhang, Haiqing Chen, Yin Zhang

In order to better understand the reason behind model behaviors (i. e., making predictions), most recent works have exploited generative models to provide complementary explanations.

counterfactual Language Modelling +1

DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework

no code implementations21 Jul 2021 Haiwen Hong, Xuan Jin, Yin Zhang, Yunqing Hu, Jingfeng Zhang, Yuan He, Hui Xue

In multimodal tasks, we find that the importance of text and image modal information is different for different input cases, and for this motivation, we propose a high-performance and highly general Dual-Router Dynamic Framework (DRDF), consisting of Dual-Router, MWF-Layer, experts and expert fusion unit.

RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition

no code implementations17 Jul 2021 Yunqing Hu, Xuan Jin, Yin Zhang, Haiwen Hong, Jingfeng Zhang, Yuan He, Hui Xue

We propose the recurrent attention multi-scale transformer (RAMS-Trans), which uses the transformer's self-attention to recursively learn discriminative region attention in a multi-scale manner.

Fine-Grained Image Classification Fine-Grained Image Recognition

Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations

1 code implementation SIGDIAL (ACL) 2021 Jingyao Zhou, Haipang Wu, Zehao Lin, Guodun Li, Yin Zhang

Then the representation of each dialogue turn is aggregated by a hierarchical structure to form the passage information, which is utilized in the current turn of DST.

Dialogue State Tracking

A Lightweight and Gradient-Stable Neural Layer

1 code implementation8 Jun 2021 Yueyao Yu, Yin Zhang

To enhance resource efficiency and model deployability of neural networks, we propose a neural-layer architecture based on Householder weighting and absolute-value activating, called Householder-absolute neural layer or simply Han-layer.

Vocal Bursts Intensity Prediction

Multi-layer Perceptron Trainability Explained via Variability

no code implementations19 May 2021 Yueyao Yu, Yin Zhang

Despite the tremendous successes of deep neural networks (DNNs) in various applications, many fundamental aspects of deep learning remain incompletely understood, including DNN trainability.

Popularity-Opportunity Bias in Collaborative Filtering

no code implementations WSDM 2021 Ziwei Zhu, Yun He, Xing Zhao, Yin Zhang, Jianling Wang, James Caverlee

This paper connects equal opportunity to popularity bias in implicit recommenders to introduce the problem of popularity-opportunity bias.

Collaborative Filtering

The simpler the better: vanilla sgd revisited

no code implementations1 Jan 2021 Yueyao Yu, Jie Wang, Wenye Li, Yin Zhang

The stochastic gradient descent (SGD) method, first proposed in 1950's, has been the foundation for deep-neural-network (DNN) training with numerous enhancements including adding a momentum or adaptively selecting learning rates, or using both strategies and more.

Image Classification speech-recognition +1

Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

no code implementations COLING 2020 Qianglong Chen, Feng Ji, Haiqing Chen, Yin Zhang

More concretely, we first introduce a novel graph-based iterative knowledge retrieval module, which iteratively retrieves concepts and entities related to the given question and its choices from multiple knowledge sources.

Language Modelling Natural Language Understanding +2

Federated Unsupervised Representation Learning

no code implementations18 Oct 2020 Fengda Zhang, Kun Kuang, Zhaoyang You, Tao Shen, Jun Xiao, Yin Zhang, Chao Wu, Yueting Zhuang, Xiaolin Li

FURL poses two new challenges: (1) data distribution shift (Non-IID distribution) among clients would make local models focus on different categories, leading to the inconsistency of representation spaces.

Federated Learning Representation Learning

Joint Partial Optimal Transport for Open Set Domain Adaptation

no code implementations11 Jul 2020 Renjun Xu, Pelen Liu, Yin Zhang, Fang Cai, Jindong Wang, Shuoying Liang, Heting Ying, Jianwei Yin

However, in a general setting when the target domain contains classes that are never observed in the source domain, namely in Open Set Domain Adaptation (OSDA), existing DA methods failed to work because of the interference of the extra unknown classes.

Domain Adaptation

Predict-then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems

no code implementations27 May 2020 Zehao Lin, Shaobo Cui, Guodun Li, Xiaoming Kang, Feng Ji, FengLin Li, Zhongzhou Zhao, Haiqing Chen, Yin Zhang

More specifically, we take advantage of a decision model to help the dialogue system decide whether to wait or answer.

Sentence

MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert

no code implementations21 May 2020 Shuke Peng, Feng Ji, Zehao Lin, Shaobo Cui, Haiqing Chen, Yin Zhang

How to build a high-quality multi-domain dialogue system is a challenging work due to its complicated and entangled dialogue state space among each domain, which seriously limits the quality of dialogue policy, and further affects the generated response.

Lifelong Learning with Searchable Extension Units

1 code implementation19 Mar 2020 Wenjin Wang, Yunqing Hu, Yin Zhang

To solve those problems, in this paper, we propose a new lifelong learning framework named Searchable Extension Units (SEU) by introducing Neural Architecture Search into lifelong learning, which breaks down the need for a predefined original model and searches for specific extension units for different tasks, without compromising the performance of the model on different tasks.

Neural Architecture Search

Consistency-Aware Recommendation for User-Generated ItemList Continuation

1 code implementation30 Dec 2019 Yun He, Yin Zhang, Weiwen Liu, James Caverlee

Complementary to methods that exploit specific content patterns (e. g., as in song-based playlists that rely on audio features), the proposed approach models the consistency of item lists based on human curation patterns, and so can be deployed across a wide range of varying item types (e. g., videos, images, books).

Chemical-protein Interaction Extraction via Gaussian Probability Distribution and External Biomedical Knowledge

1 code implementation21 Nov 2019 Cong Sun, Zhihao Yang, Leilei Su, Lei Wang, Yin Zhang, Hongfei Lin, Jian Wang

Furthermore, the Gaussian probability distribution can effectively improve the extraction performance of sentences with overlapping relations in biomedical relation extraction tasks.

Chemical-Protein Interaction Extraction Drug Discovery +2

Big-Data Clustering: K-Means or K-Indicators?

1 code implementation3 Jun 2019 Feiyu Chen, Yuchen Yang, Liwei Xu, Taiping Zhang, Yin Zhang

The K-means algorithm is arguably the most popular data clustering method, commonly applied to processed datasets in some "feature spaces", as is in spectral clustering.

Clustering

An attention-based BiLSTM-CRF approach to document-level chemical named entity recognition

1 code implementation Bioinformatics 2019 Ling Luo, Zhihao Yang, Pei Yang, Yin Zhang, Lei Wang, Hongfei Lin, Jian Wang

Motivation: In biomedical research, chemical is an important class of entities, and chemical named entity recognition (NER) is an important task in the field of biomedical information extraction.

Feature Engineering named-entity-recognition +3

Fast Similarity Search via Optimal Sparse Lifting

no code implementations NeurIPS 2018 Wenye Li, Jingwei Mao, Yin Zhang, Shuguang Cui

Similarity search is a fundamental problem in computing science with various applications and has attracted significant research attention, especially in large-scale search with high dimensions.

Fairness-Aware Recommendation of Information Curators

no code implementations9 Sep 2018 Ziwei Zhu, Jianling Wang, Yin Zhang, James Caverlee

This paper highlights our ongoing efforts to create effective information curator recommendation models that can be personalized for individual users, while maintaining important fairness properties.

Fairness

An Alternating Direction Algorithm for Matrix Completion with Nonnegative Factors

no code implementations6 Mar 2011 Yangyang Xu, Wotao Yin, Zaiwen Wen, Yin Zhang

By taking the advantages of both nonnegativity and low-rankness, one can generally obtain superior results than those of just using one of the two properties.

Information Theory Numerical Analysis Information Theory Numerical Analysis

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