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
Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry
Houssam Razouk, Leonie Benischke, Daniel Garber, Roman Kern
Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?
Yan Hu, Xu Zuo, Yujia Zhou, Xueqing Peng, Jimin Huang, Vipina K. Keloth, Vincent J. Zhang, Ruey-Ling Weng, Qingyu Chen, Xiaoqian Jiang, Kirk E. Roberts, Hua Xu
Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework
Yuping Wu, Hao Li, Hongbo Zhu, Goran Nenadic, Xiao-Jun Zeng
RUIE: Retrieval-based Unified Information Extraction using Large Language Model
Xincheng Liao, Junwen Duan, Yixi Huang, Jianxin Wang