3 May 2023 in IEEE Transactions on Knowledge and Data Engineering
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.
4 August 2025 in IEEE Transactions on Artificial Intelligence
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.