Search Results for author: Kai Sun

Found 63 papers, 24 papers with code

Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage Retrieval

no code implementations EMNLP 2021 Xueguang Ma, Minghan Li, Kai Sun, Ji Xin, Jimmy Lin

Recent work has shown that dense passage retrieval techniques achieve better ranking accuracy in open-domain question answering compared to sparse retrieval techniques such as BM25, but at the cost of large space and memory requirements.

Open-Domain Question Answering Passage Retrieval +2

Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to $K$-Level Stochastic Optimizations

no code implementations7 Jul 2024 Xiaokang Pan, Xingyu Li, Jin Liu, Tao Sun, Kai Sun, Lixing Chen, Zhe Qu

This paper provides a comprehensive generalization analysis of three representative STORM-based algorithms: STORM, COVER, and SVMR, for one, two, and $K$-level stochastic optimizations under both convex and strongly convex settings based on algorithmic stability.

Stochastic Optimization

Exclusive Style Removal for Cross Domain Novel Class Discovery

no code implementations26 Jun 2024 Yicheng Wang, Feng Liu, Junmin Liu, Zhen Fang, Kai Sun

In this paper, we explore and establish the solvability of NCD in cross domain setting with the necessary condition that style information must be removed.

Novel Class Discovery

Are Large Language Models a Good Replacement of Taxonomies?

1 code implementation17 Jun 2024 Yushi Sun, Hao Xin, Kai Sun, Yifan Ethan Xu, Xiao Yang, Xin Luna Dong, Nan Tang, Lei Chen

Unfortunately, there lacks a comprehensive benchmark that evaluates the LLMs over a wide range of taxonomies from common to specialized domains and at levels from root to leaf so that we can draw a confident conclusion.

General Knowledge Knowledge Graphs

Query-Enhanced Adaptive Semantic Path Reasoning for Inductive Knowledge Graph Completion

no code implementations4 Jun 2024 Kai Sun, Jiapu Wang, Huajie Jiang, Yongli Hu, BaoCai Yin

Conventional Knowledge graph completion (KGC) methods aim to infer missing information in incomplete Knowledge Graphs (KGs) by leveraging existing information, which struggle to perform effectively in scenarios involving emerging entities.

Inductive knowledge graph completion

Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning

no code implementations23 May 2024 Jiapu Wang, Kai Sun, Linhao Luo, Wei Wei, Yongli Hu, Alan Wee-Chung Liew, Shirui Pan, BaoCai Yin

To account for the evolving nature of TKGs, a dynamic adaptation strategy is proposed to update the LLM-generated rules with the latest events.

Estimation of Participation Factors for Power System Oscillation from Measurements

no code implementations14 May 2024 Tianwei Xia, Zhe Yu, Kai Sun, Di Shi, Kaiyang Huang

In a power system, when the participation factors of generators are computed to rank their participations into an oscillatory mode, a model-based approach is conventionally used on the linearized system model by means of the corresponding right and left eigenvectors.

MM-MATH: Advancing Multimodal Math Evaluation with Process Evaluation and Fine-grained Classification

1 code implementation7 Apr 2024 Kai Sun, Yushi Bai, Ji Qi, Lei Hou, Juanzi Li

This highlights the challenging nature of our benchmark for existing models and the significant gap between the multimodal reasoning capabilities of current models and humans.

Image Comprehension Math +1

A Semi-Analytical Approach for State-Space Electromagnetic Transient Simulation Using the Differential Transformation

no code implementations19 Dec 2023 Min Xiong, Kaiyang Huang, Yang Liu, Rui Yao, Kai Sun, Feng Qiu

Case studies are conducted on EMT models of the IEEE 39-bus system and a synthetic 390-bus system to demonstrate the merits of the new simulation approach against traditional methods.

AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation

no code implementations6 Dec 2023 Xinzhou Wang, Yikai Wang, Junliang Ye, Zhengyi Wang, Fuchun Sun, Pengkun Liu, Ling Wang, Kai Sun, Xintong Wang, Bin He

Extensive experiments demonstrate the capability of our method in generating high-flexibility text-guided 3D models from the monocular video, while also showing improved reconstruction performance over existing non-rigid reconstruction methods.

3D Generation Denoising +1

Anaphor Assisted Document-Level Relation Extraction

1 code implementation28 Oct 2023 Chonggang Lu, Richong Zhang, Kai Sun, Jaein Kim, Cunwang Zhang, Yongyi Mao

Existing methods focus on building a heterogeneous document graph to model the internal structure of an entity and the external interaction between entities.

Document-level Relation Extraction Relation +1

Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?

1 code implementation20 Aug 2023 Kai Sun, Yifan Ethan Xu, Hanwen Zha, Yue Liu, Xin Luna Dong

Since the recent prosperity of Large Language Models (LLMs), there have been interleaved discussions regarding how to reduce hallucinations from LLM responses, how to increase the factuality of LLMs, and whether Knowledge Graphs (KGs), which store the world knowledge in a symbolic form, will be replaced with LLMs.

Knowledge Graphs World Knowledge

Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement

no code implementations18 May 2023 Samuel Mensah, Kai Sun, Nikolaos Aletras

State-of-the-art target-oriented opinion word extraction (TOWE) models typically use BERT-based text encoders that operate on the word level, along with graph convolutional networks (GCNs) that incorporate syntactic information extracted from syntax trees.

Sentence target-oriented opinion words extraction

Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction

no code implementations28 Feb 2023 Kai Sun, Richong Zhang, Samuel Mensah, Nikolaos Aletras, Yongyi Mao, Xudong Liu

Inspired by the theoretical foundations in domain adaptation [2], we propose a new SSL approach that opts for selecting target samples whose model output from a domain-specific teacher and student network disagree on the unlabelled target data, in an effort to boost the target domain performance.

Aspect Extraction Domain Adaptation +1

Semi-Analytical Electromagnetic Transient Simulation Using Differential Transformation

no code implementations18 Feb 2023 Min Xiong, Rui Yao, Yang Liu, Kai Sun, Feng Qiu

For electromagnetic transient (EMT) simulation of a power system, a state-space-based approach needs to solve state-space EMT equations by using numerical integration methods, e. g., the Euler method, Runge-Kutta methods, and trapezoidal-rule method, at small time steps.

Numerical Integration

Digital Asset Valuation: A Study on Domain Names, Email Addresses, and NFTs

no code implementations6 Oct 2022 Kai Sun

We further propose improvements to make the model more aware of the time sensitivity of transactions and the popularity of assets.

Preparing data for pathological artificial intelligence with clinical-grade performance

no code implementations22 May 2022 Yuanqing Yang, Kai Sun, Yanhua Gao, Kuangsong Wang, Gang Yu

The digital pathology is fundamental of clinical-grade PAI, and the techniques of data standardization and weakly supervised learning methods based on whole slide image (WSI) are effective ways to overcome obstacles of performance reproduction.

Weakly-supervised Learning

Machine Learning based Optimal Feedback Control for Microgrid Stabilization

no code implementations9 Mar 2022 Tianwei Xia, Kai Sun, Wei Kang

A case study is carried out for a microgrid model based on a modified Kundur two-area system to test the real-time performance of the proposed control scheme.

BIG-bench Machine Learning

Data-Driven Computational Methods for the Domain of Attraction and Zubov's Equation

no code implementations29 Dec 2021 Wei Kang, Kai Sun, Liang Xu

We prove that a neural network approximation exists for the Lyapunov function of power systems such that the approximation error is a cubic polynomial of the number of generators.

An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction

1 code implementation EMNLP 2021 Samuel Mensah, Kai Sun, Nikolaos Aletras

Target-oriented opinion words extraction (TOWE) (Fan et al., 2019b) is a new subtask of target-oriented sentiment analysis that aims to extract opinion words for a given aspect in text.

Position target-oriented opinion words extraction +1

XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data

2 code implementations26 May 2021 Eloise Withnell, XiaoYu Zhang, Kai Sun, Yike Guo

To the best of our knowledge, XOmiVAE is one of the first activation level-based interpretable deep learning models explaining novel clusters generated by VAE.

Classification Clustering +1

Multi-scale super-resolution generation of low-resolution scanned pathological images

1 code implementation15 May 2021 Kai Sun, Yanhua Gao, Ting Xie, Xun Wang, Qingqing Yang, Le Chen, Kuansong Wang, Gang Yu

We design a strategy to scan slides with low resolution (5X) and a super-resolution method is proposed to restore the image details when in diagnosis.

Generative Adversarial Network SSIM +1

A Replication Study of Dense Passage Retriever

1 code implementation12 Apr 2021 Xueguang Ma, Kai Sun, Ronak Pradeep, Jimmy Lin

Text retrieval using learned dense representations has recently emerged as a promising alternative to "traditional" text retrieval using sparse bag-of-words representations.

Open-Domain Question Answering Text Retrieval

Deep Gradient Projection Networks for Pan-sharpening

1 code implementation CVPR 2021 Shuang Xu, Jiangshe Zhang, Zixiang Zhao, Kai Sun, Junmin Liu, Chunxia Zhang

Specifically, two optimization problems regularized by the deep prior are formulated, and they are separately responsible for the generative models for panchromatic images and low resolution multispectral images.

OmiEmbed: a unified multi-task deep learning framework for multi-omics data

1 code implementation3 Feb 2021 XiaoYu Zhang, Yuting Xing, Kai Sun, Yike Guo

To tackle this problem and pave the way for machine learning aided precision medicine, we proposed a unified multi-task deep learning framework named OmiEmbed to capture biomedical information from high-dimensional omics data with the deep embedding and downstream task modules.

BIG-bench Machine Learning Decision Making +2

Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data

no code implementations Findings (EMNLP) 2021 Dian Yu, Kai Sun, Dong Yu, Claire Cardie

In spite of much recent research in the area, it is still unclear whether subject-area question-answering data is useful for machine reading comprehension (MRC) tasks.

Machine Reading Comprehension Multiple-choice +1

A Blockchain-based Trust System for Decentralised Applications: When trustless needs trust

no code implementations26 Jan 2021 Nguyen Truong, Gyu Myoung Lee, Kai Sun, Florian Guitton, Yike Guo

Blockchain technology has been envisaged to commence an era of decentralised applications and services (DApps) without the need for a trusted intermediary.

Cryptography and Security Distributed, Parallel, and Cluster Computing

Towards Reducing Severe Defocus Spread Effects for Multi-Focus Image Fusion via an Optimization Based Strategy

1 code implementation29 Dec 2020 Shuang Xu, Lizhen Ji, Zhe Wang, Pengfei Li, Kai Sun, Chunxia Zhang, Jiangshe Zhang

According to the idea that each local region in the fused image should be similar to the sharpest one among source images, this paper presents an optimization-based approach to reduce defocus spread effects.


Aligning geographic entities from historical maps for building knowledge graphs

no code implementations5 Dec 2020 Kai Sun, Yingjie Hu, Jia Song, Yunqiang Zhu

Despite their valuable content, it is often challenging to access and use the information in historical maps, due to their forms of paper-based maps or scanned images.

Knowledge Graphs

Privacy Preservation in Federated Learning: An insightful survey from the GDPR Perspective

no code implementations10 Nov 2020 Nguyen Truong, Kai Sun, Siyao Wang, Florian Guitton, Yike Guo

Furthermore, in the era of the Internet of Things and big data in which data is essentially distributed, transferring a vast amount of data to a data centre for processing seems to be a cumbersome solution.

Federated Learning Privacy Preserving

Adding Chit-Chat to Enhance Task-Oriented Dialogues

1 code implementation NAACL 2021 Kai Sun, Seungwhan Moon, Paul Crook, Stephen Roller, Becka Silvert, Bing Liu, Zhiguang Wang, Honglei Liu, Eunjoon Cho, Claire Cardie

Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e. g., booking hotels), open-domain chatbots aim at making socially engaging conversations.

Dialogue Generation Dialogue Understanding +1

When Image Decomposition Meets Deep Learning: A Novel Infrared and Visible Image Fusion Method

no code implementations2 Sep 2020 Zixiang Zhao, Jiangshe Zhang, Shuang Xu, Kai Sun, Chunxia Zhang, Junmin Liu

The core idea is that the encoder decomposes an image into base and detail feature maps with low- and high-frequency information, respectively, and that the decoder is responsible for the original image reconstruction.

Decoder Image Enhancement +2

Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations

no code implementations EMNLP 2020 Kai Sun, Richong Zhang, Samuel Mensah, Yongyi Mao, Xudong Liu

The idea of using multi-task learning approaches to address the joint extraction of entity and relation is motivated by the relatedness between the entity recognition task and the relation classification task.

General Classification Multi-Task Learning +3

Dialogue-Based Relation Extraction

3 code implementations ACL 2020 Dian Yu, Kai Sun, Claire Cardie, Dong Yu

We present the first human-annotated dialogue-based relation extraction (RE) dataset DialogRE, aiming to support the prediction of relation(s) between two arguments that appear in a dialogue.

Ranked #6 on Dialog Relation Extraction on DialogRE (F1c (v1) metric)

Dialog Relation Extraction Relation +1

MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships

1 code implementation CVPR 2020 Yongjian Chen, Lei Tai, Kai Sun, Mingyang Li

Monocular 3D object detection is an essential component in autonomous driving while challenging to solve, especially for those occluded samples which are only partially visible.

Autonomous Driving Monocular 3D Object Detection +3

Unsupervised Annotation of Phenotypic Abnormalities via Semantic Latent Representations on Electronic Health Records

1 code implementation10 Nov 2019 Jingqing Zhang, Xiao-Yu Zhang, Kai Sun, Xian Yang, Chengliang Dai, Yike Guo

The extraction of phenotype information which is naturally contained in electronic health records (EHRs) has been found to be useful in various clinical informatics applications such as disease diagnosis.

Computational Efficiency

Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree

no code implementations IJCNLP 2019 Kai Sun, Richong Zhang, Samuel Mensah, Yongyi Mao, Xudong Liu

We propose a method based on neural networks to identify the sentiment polarity of opinion words expressed on a specific aspect of a sentence.

Representation Learning Sentence +2

Improving Pre-Trained Multilingual Model with Vocabulary Expansion

no code implementations CONLL 2019 Hai Wang, Dian Yu, Kai Sun, Jianshu Chen, Dong Yu

However, in multilingual setting, it is extremely resource-consuming to pre-train a deep language model over large-scale corpora for each language.

Language Modelling Machine Reading Comprehension +6

Improving Pre-Trained Multilingual Models with Vocabulary Expansion

no code implementations26 Sep 2019 Hai Wang, Dian Yu, Kai Sun, Janshu Chen, Dong Yu

However, in multilingual setting, it is extremely resource-consuming to pre-train a deep language model over large-scale corpora for each language.

Language Modelling Machine Reading Comprehension +6

Sem-LSD: A Learning-based Semantic Line Segment Detector

1 code implementation14 Sep 2019 Yi Sun, Xushen Han, Kai Sun, Boren Li, Yongjiang Chen, Mingyang Li

Combined with high-level semantics, Sem-LS is more robust under cluttered environment compared with existing line-shaped representations.

Line Segment Detection Loop Closure Detection

Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification

4 code implementations17 Aug 2019 Xiao-Yu Zhang, Jingqing Zhang, Kai Sun, Xian Yang, Chengliang Dai, Yike Guo

The training procedure of OmiVAE is comprised of an unsupervised phase without the classifier and a supervised phase with the classifier.

Classification Decision Making +3

AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data

no code implementations12 Jul 2019 Zheng Gao, Lin Guo, Chi Ma, Xiao Ma, Kai Sun, Hang Xiang, Xiaoqiang Zhu, Hongsong Li, Xiaozhong Liu

Anomaly detection is facing with emerging challenges in many important industry domains, such as cyber security and online recommendation and advertising.

Anomaly Detection

Improving Question Answering with External Knowledge

1 code implementation WS 2019 Xiaoman Pan, Kai Sun, Dian Yu, Jianshu Chen, Heng Ji, Claire Cardie, Dong Yu

We focus on multiple-choice question answering (QA) tasks in subject areas such as science, where we require both broad background knowledge and the facts from the given subject-area reference corpus.

Multiple-choice Question Answering

DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension

1 code implementation1 Feb 2019 Kai Sun, Dian Yu, Jianshu Chen, Dong Yu, Yejin Choi, Claire Cardie

DREAM is likely to present significant challenges for existing reading comprehension systems: 84% of answers are non-extractive, 85% of questions require reasoning beyond a single sentence, and 34% of questions also involve commonsense knowledge.

Dialogue Understanding Multiple-choice +3

Visualizing and Understanding Deep Neural Networks in CTR Prediction

no code implementations22 Jun 2018 Lin Guo, Hui Ye, Wenbo Su, Henhuan Liu, Kai Sun, Hang Xiang

Recently, many works have been done on visualizing and analyzing the mechanism of deep neural networks in the areas of image processing and natural language processing.

Click-Through Rate Prediction

A vision based system for underwater docking

no code implementations12 Dec 2017 Shuang Liu, Mete Ozay, Takayuki Okatani, Hongli Xu, Kai Sun, Yang Lin

In the experiments, we first evaluate performance of the proposed detection module on UDID and its deformed variations.

Pose Estimation Position

Recurrent Polynomial Network for Dialogue State Tracking

no code implementations14 Jul 2015 Kai Sun, Qizhe Xie, Kai Yu

Dialogue state tracking (DST) is a process to estimate the distribution of the dialogue states as a dialogue progresses.

dialog state tracking Dialogue State Tracking

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