Jiuyang Tang

Jiuyang Tang

Auto-generated profile, based on publicly available information

Jiuyang Tang

Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, Hunan, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 May 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Open access
WZWeixin Zeng
Weixin Zeng
XZXiang Zhao
Xiang Zhao
ZTZhen Tan
Zhen Tan
JTJiuyang Tang
Jiuyang Tang
XCXueqi Cheng
Xueqi Cheng
Entity alignment (EA) identifies equivalent entities that locate in different knowledge graphs (KGs), and has attracted growing research interests over the last few years with the advancement of KG embedding techniques. Although a pile of embedding-based EA frameworks have been developed, they mainly focus on improving the performance of entity representation learning , while largely overlook the subsequent stage that matches KGs in entity embedding spaces . Nevertheless, accurately matching entities based on learned entity representations is crucial to the overall alignment performance, as it coordinates individual alignment decisions and determines the global matching result. Hence, it is essential to understand how well existing solutions for matching KGs in entity embedding spaces perform on present benchmarks, as well as their strengths and weaknesses. To this end, in this article we provide a comprehensive survey and evaluation of matching algorithms for KGs in entity embedding spaces in terms of effectiveness and efficiency on both classic settings and new scenarios that better mirror real-life challenges. Based on in-depth analysis, we provide useful insights into the design trade-offs and good paradigms of existing works, and suggest promising directions for future development.

21 October 2023
Verified
Conference Paper
Open access
HGHao Guo
Hao Guo
WZWeixin Zeng
Weixin Zeng
JTJiuyang Tang
Jiuyang Tang
XZXiang Zhao
Xiang Zhao

1 November 2014
Verified
Conference Paper
Closed access
GTGuoming Tang
Guoming Tang
KWKui Wu
Kui Wu
JLJingsheng Lei
Jingsheng Lei
JTJiuyang Tang
Jiuyang Tang
Energy disaggregation is to discover the energy consumption of individual appliances from their aggregated energy values. To solve the problem, most existing approaches rely on either appliances' signatures or their state transition patterns, both hard to obtain in practice. Aiming at developing a simple, universal model that works without depending on sophisticated machine learning techniques or auxiliary equipments, we make use of easily accessible knowledge of appliances and the sparsity of the switching events to design a Sparse Switching Event Recovering (SSER) method. By minimizing the total variation (TV) of the (sparse) event matrix, SSER can effectively recover the individual energy consumption values from the aggregated ones. To speed up the process, a Parallel Local Optimization Algorithm (PLOA) is proposed to solve the problem in active epochs of appliance activities in parallel. Using real-world trace data, we compare the performance of our method with that of the state-of-the-art solutions, including the popular Least Square Estimation (LSE) methods and a recently-developed machine learning method using iterative Hidden Markov Model (HMM). The results show that our approach has an overall better performance in both detection accuracy and overhead.

21 October 2024
Verified
Conference Paper
Open access
RZRunhao Zhao
Runhao Zhao
JTJiuyang Tang
Jiuyang Tang
WZWeixin Zeng
Weixin Zeng
ZCZiyang Chen
Ziyang Chen
XZXiang Zhao
Xiang Zhao
Knowledge Graph Question Generation (KGQG) is the task of generating natural language questions based on the given knowledge graph (KG). Although extensively explored in recent years, prevailing models predominantly depend on labelled data for training deep learning models or employ large parametric frameworks, e.g., Large Language Models (LLMs), which can incur significant deployment costs and pose practical implementation challenges. To address these issues, in this work, we put forward a zero-shot, multi-agent KGQG framework. This framework integrates the capabilities of LLMs with small models to facilitate cost-effective, high-quality question generation. In specific, we develop a professional editorial team architecture accompanied by two workflow optimization tools to reduce unproductive collaboration among LLMs-based agents and enhance the robustness of the system. Extensive experiments demonstrate that our proposed framework derives the new state-of-the-art performance on the zero-shot KGQG tasks, with relative gains of 20.24% and 13.57% on two KGQG datasets, respectively, which rival fully supervised state-of-the-art models.

11 July 2021
Verified
Conference Paper
Open access
JLJinzhi Liao
Jinzhi Liao
XZXiang Zhao
Xiang Zhao
XLXinyi Li
Xinyi Li
LZLingling Zhang
Lingling Zhang
JTJiuyang Tang
Jiuyang Tang
Retrieving event instances from texts is pivotal to various natural language processing applications (e.g., automatic question answering and dialogue systems), and the first task to perform is event detection. There are two related sub-tasks therein-trigger identification and type classification, and the former is considered to play a dominant role. Nevertheless, it is notoriously challenging to predict event triggers right. To handle the task, existing work has made tremendous progress by incorporating manual features, data augmentation and neural networks, etc. Due to the scarcity of data and insufficient representation of trigger words, however, they still fail to precisely determine the spans of triggers (coined as trigger span detection problem). To address the challenge, we propose to learn discriminative neural representations (DNR) from texts. Specifically, our DNR model tackles the trigger span detection problem by exploiting two novel techniques: 1) a contrastive learning strategy, which enlarges the discrepancy between representations of words inside and outside triggers; and 2) a Mixspan strategy, which better trains the model to differentiate words nearby triggers' span boundaries. Extensive experiments on benchmarks-ACE2005 and TAC2015-demonstrate the superiority of our DNR model, leading to state-of-the-art performance.

4 August 2025 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Closed access
RZRunhao Zhao
Runhao Zhao
WZWeixin Zeng
Weixin Zeng
JTJiuyang Tang
Jiuyang Tang
FTFen Tian
Fen Tian
XZXiang Zhao
Xiang Zhao
Educational question answering plays an extremely important role in online education all over the world. Among these, Educational Knowledge Graph Question Answering (EKGQA) focuses on extracting knowledge from the educational knowledge base to answer educational questions. Although some work has been done, the scarcity of the real Chinese annotated dataset has restricted the development of EKGQA. Unlike current datasets where the questions are direct, educational questions asked by learners may involve diverse, mixed cognitive expressions and language styles due to differences in personal experiences, cultural backgrounds, and cognitive levels. To address these issues, in this paper, we proposed to benchmark such challenges for EKGQA by establishing a more realistic dataset EDUCEQ. It contains 236.3k questions in 12 categories. Compared with existing datasets, EDUCEQ features two more authentic features - diverse cognitive expressions and various language styles. Additionally, we have conducted an in-depth evaluation of the EDUCEQ dataset and developed a robust LLM-based EKGQA method that established competitive benchmarks for future research. EDUCEQ is the first dataset to portray a more realistic view of educational phenomena from a cognitive and computational linguistics perspective, which is beneficial to educational knowledge graph question answering, AI4Education and also the online education field in general.