Alert button
Picture for Kai Sun

Kai Sun

Alert button

Department of Biomedical Engineering, School of Basic Medical Sciences, Central South University, Changsha, China

Anaphor Assisted Document-Level Relation Extraction

Oct 28, 2023
Chonggang Lu, Richong Zhang, Kai Sun, Jaein Kim, Cunwang Zhang, Yongyi Mao

Document-level relation extraction (DocRE) involves identifying relations between entities distributed in multiple sentences within a document. Existing methods focus on building a heterogeneous document graph to model the internal structure of an entity and the external interaction between entities. However, there are two drawbacks in existing methods. On one hand, anaphor plays an important role in reasoning to identify relations between entities but is ignored by these methods. On the other hand, these methods achieve cross-sentence entity interactions implicitly by utilizing a document or sentences as intermediate nodes. Such an approach has difficulties in learning fine-grained interactions between entities across different sentences, resulting in sub-optimal performance. To address these issues, we propose an Anaphor-Assisted (AA) framework for DocRE tasks. Experimental results on the widely-used datasets demonstrate that our model achieves a new state-of-the-art performance.

* Accepted to EMNLP 2023 Main Conference 
Viaarxiv icon

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

Aug 20, 2023
Kai Sun, Yifan Ethan Xu, Hanwen Zha, Yue Liu, Xin Luna Dong

Figure 1 for Head-to-Tail: How Knowledgeable are Large Language Models (LLM)? A.K.A. Will LLMs Replace Knowledge Graphs?
Figure 2 for Head-to-Tail: How Knowledgeable are Large Language Models (LLM)? A.K.A. Will LLMs Replace Knowledge Graphs?
Figure 3 for Head-to-Tail: How Knowledgeable are Large Language Models (LLM)? A.K.A. Will LLMs Replace Knowledge Graphs?
Figure 4 for Head-to-Tail: How Knowledgeable are Large Language Models (LLM)? A.K.A. Will LLMs Replace Knowledge Graphs?

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. In this paper, we try to answer these questions from a new angle: How knowledgeable are LLMs? To answer this question, we constructed Head-to-Tail, a benchmark that consists of 18K question-answer (QA) pairs regarding head, torso, and tail facts in terms of popularity. We designed an automated evaluation method and a set of metrics that closely approximate the knowledge an LLM confidently internalizes. Through a comprehensive evaluation of 14 publicly available LLMs, we show that existing LLMs are still far from being perfect in terms of their grasp of factual knowledge, especially for facts of torso-to-tail entities.

Viaarxiv icon

The Potential and Pitfalls of using a Large Language Model such as ChatGPT or GPT-4 as a Clinical Assistant

Jul 16, 2023
Jingqing Zhang, Kai Sun, Akshay Jagadeesh, Mahta Ghahfarokhi, Deepa Gupta, Ashok Gupta, Vibhor Gupta, Yike Guo

Figure 1 for The Potential and Pitfalls of using a Large Language Model such as ChatGPT or GPT-4 as a Clinical Assistant
Figure 2 for The Potential and Pitfalls of using a Large Language Model such as ChatGPT or GPT-4 as a Clinical Assistant
Figure 3 for The Potential and Pitfalls of using a Large Language Model such as ChatGPT or GPT-4 as a Clinical Assistant
Figure 4 for The Potential and Pitfalls of using a Large Language Model such as ChatGPT or GPT-4 as a Clinical Assistant

Recent studies have demonstrated promising performance of ChatGPT and GPT-4 on several medical domain tasks. However, none have assessed its performance using a large-scale real-world electronic health record database, nor have evaluated its utility in providing clinical diagnostic assistance for patients across a full range of disease presentation. We performed two analyses using ChatGPT and GPT-4, one to identify patients with specific medical diagnoses using a real-world large electronic health record database and the other, in providing diagnostic assistance to healthcare workers in the prospective evaluation of hypothetical patients. Our results show that GPT-4 across disease classification tasks with chain of thought and few-shot prompting can achieve performance as high as 96% F1 scores. For patient assessment, GPT-4 can accurately diagnose three out of four times. However, there were mentions of factually incorrect statements, overlooking crucial medical findings, recommendations for unnecessary investigations and overtreatment. These issues coupled with privacy concerns, make these models currently inadequate for real world clinical use. However, limited data and time needed for prompt engineering in comparison to configuration of conventional machine learning workflows highlight their potential for scalability across healthcare applications.

* This manuscript is pre-print and in peer review. Supplementary materials will be published later 
Viaarxiv icon

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

May 18, 2023
Samuel Mensah, Kai Sun, Nikolaos Aletras

Figure 1 for Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement
Figure 2 for Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement
Figure 3 for Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement
Figure 4 for Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement

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. These methods achieve limited gains with GCNs and have difficulty using BERT wordpieces. Meanwhile, BERT wordpieces are known to be effective at representing rare words or words with insufficient context information. To address this issue, this work trades syntax trees for BERT wordpieces by entirely removing the GCN component from the methods' architectures. To enhance TOWE performance, we tackle the issue of aspect representation loss during encoding. Instead of solely utilizing a sentence as the input, we use a sentence-aspect pair. Our relatively simple approach achieves state-of-the-art results on benchmark datasets and should serve as a strong baseline for further research.

* Accepted at ACL 2023 
Viaarxiv icon

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

Feb 28, 2023
Kai Sun, Richong Zhang, Samuel Mensah, Nikolaos Aletras, Yongyi Mao, Xudong Liu

Figure 1 for Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction
Figure 2 for Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction
Figure 3 for Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction
Figure 4 for Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction

Opinion target extraction (OTE) or aspect extraction (AE) is a fundamental task in opinion mining that aims to extract the targets (or aspects) on which opinions have been expressed. Recent work focus on cross-domain OTE, which is typically encountered in real-world scenarios, where the testing and training distributions differ. Most methods use domain adversarial neural networks that aim to reduce the domain gap between the labelled source and unlabelled target domains to improve target domain performance. However, this approach only aligns feature distributions and does not account for class-wise feature alignment, leading to suboptimal results. Semi-supervised learning (SSL) has been explored as a solution, but is limited by the quality of pseudo-labels generated by the model. 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. Extensive experiments on benchmark cross-domain OTE datasets show that this approach is effective and performs consistently well in settings with large domain shifts.

* Accepted at TheWebConf 2023 
Viaarxiv icon

Preparing data for pathological artificial intelligence with clinical-grade performance

May 22, 2022
Yuanqing Yang, Kai Sun, Yanhua Gao, Kuangsong Wang, Gang Yu

Figure 1 for Preparing data for pathological artificial intelligence with clinical-grade performance
Figure 2 for Preparing data for pathological artificial intelligence with clinical-grade performance
Figure 3 for Preparing data for pathological artificial intelligence with clinical-grade performance
Figure 4 for Preparing data for pathological artificial intelligence with clinical-grade performance

[Purpose] The pathology is decisive for disease diagnosis, but relies heavily on the experienced pathologists. Recently, pathological artificial intelligence (PAI) is thought to improve diagnostic accuracy and efficiency. However, the high performance of PAI based on deep learning in the laboratory generally cannot be reproduced in the clinic. [Methods] Because the data preparation is important for PAI, the paper has reviewed PAI-related studies in the PubMed database published from January 2017 to February 2022, and 118 studies were included. The in-depth analysis of methods for preparing data is performed, including obtaining slides of pathological tissue, cleaning, screening, and then digitizing. Expert review, image annotation, dataset division for model training and validation are also discussed. We further discuss the reasons why the high performance of PAI is not reproducible in the clinical practices and show some effective ways to improve clinical performances of PAI. [Results] The robustness of PAI depend on randomized collection of representative disease slides, including rigorous quality control and screening, correction of digital discrepancies, reasonable annotation, and the amount of data. 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. [Conclusion] The representative data, the amount of labeling and consistency from multi-centers is the key to performance reproduction. The digital pathology for clinical diagnosis, data standardization and technique of WSI-based weakly supervised learning hopefully build clinical-grade PAI. Keywords: pathological artificial intelligence; data preparation; clinical-grade; deep learning

Viaarxiv icon

Machine Learning based Optimal Feedback Control for Microgrid Stabilization

Mar 09, 2022
Tianwei Xia, Kai Sun, Wei Kang

Figure 1 for Machine Learning based Optimal Feedback Control for Microgrid Stabilization
Figure 2 for Machine Learning based Optimal Feedback Control for Microgrid Stabilization
Figure 3 for Machine Learning based Optimal Feedback Control for Microgrid Stabilization
Figure 4 for Machine Learning based Optimal Feedback Control for Microgrid Stabilization

Microgrids have more operational flexibilities as well as uncertainties than conventional power grids, especially when renewable energy resources are utilized. An energy storage based feedback controller can compensate undesired dynamics of a microgrid to improve its stability. However, the optimal feedback control of a microgrid subject to a large disturbance needs to solve a Hamilton-Jacobi-Bellman problem. This paper proposes a machine learning-based optimal feedback control scheme. Its training dataset is generated from a linear-quadratic regulator and a brute-force method respectively addressing small and large disturbances. Then, a three-layer neural network is constructed from the data for the purpose of optimal feedback control. 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.

* Accepted by 2022 IEEE PES General Meeting in Denver, CO 
Viaarxiv icon

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

Dec 29, 2021
Wei Kang, Kai Sun, Liang Xu

Figure 1 for Data-Driven Computational Methods for the Domain of Attraction and Zubov's Equation
Figure 2 for Data-Driven Computational Methods for the Domain of Attraction and Zubov's Equation
Figure 3 for Data-Driven Computational Methods for the Domain of Attraction and Zubov's Equation
Figure 4 for Data-Driven Computational Methods for the Domain of Attraction and Zubov's Equation

This paper deals with a special type of Lyapunov functions, namely the solution of Zubov's equation. Such a function can be used to characterize the domain of attraction for systems of ordinary differential equations. We derive and prove an integral form solution to Zubov's equation. For numerical computation, we develop two data-driven methods. One is based on the integration of an augmented system of differential equations; and the other one is based on deep learning. The former is effective for systems with a relatively low state space dimension and the latter is developed for high dimensional problems. The deep learning method is applied to a New England 10-generator power system model. 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. The error convergence rate as a function of n, the number of neurons, is proved.

* 20 pages, 10 figures 
Viaarxiv icon

PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving

Dec 23, 2021
Pengchuan Xiao, Zhenlei Shao, Steven Hao, Zishuo Zhang, Xiaolin Chai, Judy Jiao, Zesong Li, Jian Wu, Kai Sun, Kun Jiang, Yunlong Wang, Diange Yang

Figure 1 for PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving
Figure 2 for PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving
Figure 3 for PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving
Figure 4 for PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving

The accelerating development of autonomous driving technology has placed greater demands on obtaining large amounts of high-quality data. Representative, labeled, real world data serves as the fuel for training deep learning networks, critical for improving self-driving perception algorithms. In this paper, we introduce PandaSet, the first dataset produced by a complete, high-precision autonomous vehicle sensor kit with a no-cost commercial license. The dataset was collected using one 360{\deg} mechanical spinning LiDAR, one forward-facing, long-range LiDAR, and 6 cameras. The dataset contains more than 100 scenes, each of which is 8 seconds long, and provides 28 types of labels for object classification and 37 types of labels for semantic segmentation. We provide baselines for LiDAR-only 3D object detection, LiDAR-camera fusion 3D object detection and LiDAR point cloud segmentation. For more details about PandaSet and the development kit, see https://scale.com/open-datasets/pandaset.

* This paper has been published on ITSC'2021, please check the website of the PandaSet for more information: https://pandaset.org/ 
Viaarxiv icon

Partial Symbol Recovery for Interference Resilience in Low-Power Wide Area Networks

Sep 08, 2021
Kai Sun, Zhimeng Yin, Weiwei Chen, Shuai Wang, Zeyu Zhang, Tian He

Figure 1 for Partial Symbol Recovery for Interference Resilience in Low-Power Wide Area Networks
Figure 2 for Partial Symbol Recovery for Interference Resilience in Low-Power Wide Area Networks
Figure 3 for Partial Symbol Recovery for Interference Resilience in Low-Power Wide Area Networks
Figure 4 for Partial Symbol Recovery for Interference Resilience in Low-Power Wide Area Networks

Recent years have witnessed the proliferation of Low-power Wide Area Networks (LPWANs) in the unlicensed band for various Internet-of-Things (IoT) applications. Due to the ultra-low transmission power and long transmission duration, LPWAN devices inevitably suffer from high power Cross Technology Interference (CTI), such as interference from Wi-Fi, coexisting in the same spectrum. To alleviate this issue, this paper introduces the Partial Symbol Recovery (PSR) scheme for improving the CTI resilience of LPWAN. We verify our idea on LoRa, a widely adopted LPWAN technique, as a proof of concept. At the PHY layer, although CTI has much higher power, its duration is relatively shorter compared with LoRa symbols, leaving part of a LoRa symbol uncorrupted. Moreover, due to its high redundancy, LoRa chips within a symbol are highly correlated. This opens the possibility of detecting a LoRa symbol with only part of the chips. By examining the unique frequency patterns in LoRa symbols with time-frequency analysis, our design effectively detects the clean LoRa chips that are free of CTI. This enables PSR to only rely on clean LoRa chips for successfully recovering from communication failures. We evaluate our PSR design with real-world testbeds, including SX1280 LoRa chips and USRP B210, under Wi-Fi interference in various scenarios. Extensive experiments demonstrate that our design offers reliable packet recovery performance, successfully boosting the LoRa packet reception ratio from 45.2% to 82.2% with a performance gain of 1.8 times.

Viaarxiv icon