Information Extraction
Information extraction (IE) focuses on automatically extracting structured information from unstructured or semi-structured text, aiming to convert raw data into usable formats for various applications. Current research emphasizes unified IE frameworks, often leveraging large language models (LLMs) and incorporating retrieval-augmented generation (RAG) techniques, along with advancements in neural architectures like LSTMs and transformers. This field is crucial for knowledge base construction, enabling efficient data analysis across diverse domains like healthcare, finance, and humanitarian aid, and improving the accuracy and speed of data processing in numerous applications.
Papers
Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction
Xuming Hu, Shiao Meng, Chenwei Zhang, Xiangli Yang, Lijie Wen, Irwin King, Philip S. Yu
MEE: A Novel Multilingual Event Extraction Dataset
Amir Pouran Ben Veyseh, Javid Ebrahimi, Franck Dernoncourt, Thien Huu Nguyen
TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents
Zhanzhan Cheng, Peng Zhang, Can Li, Qiao Liang, Yunlu Xu, Pengfei Li, Shiliang Pu, Yi Niu, Fei Wu
Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration
Zhenyu Zhang, Bowen Yu, Haiyang Yu, Tingwen Liu, Cheng Fu, Jingyang Li, Chengguang Tang, Jian Sun, Yongbin Li