Entity Mention
Entity mention, the identification and classification of named entities within text, is a core task in natural language processing aiming to extract structured information from unstructured data. Current research focuses on improving accuracy and robustness across diverse domains and languages, employing techniques like transformer-based models, graph neural networks, and knowledge base integration to enhance entity recognition and relation extraction. This work is crucial for applications ranging from knowledge graph construction and question answering to improved search and information retrieval, impacting various fields including legal tech, biomedical research, and financial analysis. Furthermore, ongoing efforts address challenges like handling ambiguous entity mentions, hallucinations in large language models, and the efficient processing of low-resource languages.
Papers
SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents
Qi Zhang, Zhijia Chen, Huitong Pan, Cornelia Caragea, Longin Jan Latecki, Eduard Dragut
SEG:Seeds-Enhanced Iterative Refinement Graph Neural Network for Entity Alignment
Wei Ai, Yinghui Gao, Jianbin Li, Jiayi Du, Tao Meng, Yuntao Shou, Keqin Li
MELO: An Evaluation Benchmark for Multilingual Entity Linking of Occupations
Federico Retyk, Luis Gasco, Casimiro Pio Carrino, Daniel Deniz, Rabih Zbib
OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting
Xukai Liu, Ye Liu, Kai Zhang, Kehang Wang, Qi Liu, Enhong Chen