Entity Classification
Entity classification, a core task in natural language processing, aims to automatically assign semantic labels (e.g., person, location, organization) to textual mentions. Current research emphasizes improving accuracy by addressing biases in training data and leveraging advanced architectures like graph neural networks and large language models, often incorporating contextual information and spatial relationships within documents to enhance performance. This work is crucial for advancing applications such as information extraction, knowledge base construction, and document understanding, particularly in complex scenarios involving diverse document layouts and multilingual content.
Papers
P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models
Guochao Jiang, Zepeng Ding, Yuchen Shi, Deqing Yang
Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents
Yanfei Dong, Lambert Deng, Jiazheng Zhang, Xiaodong Yu, Ting Lin, Francesco Gelli, Soujanya Poria, Wee Sun Lee