ChatGPT is a Potential Zero-Shot Dependency Parser

no code implementations • 25 Oct 2023 • Boda Lin, Xinyi Zhou, Binghao Tang, Xiaocheng Gong, Si Li

Pre-trained language models have been widely used in dependency parsing task and have achieved significant improvements in parser performance.

Dependency Parsing

Type-aware Decoding via Explicitly Aggregating Event Information for Document-level Event Extraction

no code implementations • 16 Oct 2023 • Gang Zhao, Yidong Shi, Shudong Lu, Xinjie Yang, Guanting Dong, Jian Xu, Xiaocheng Gong, Si Li

Although previous methods attempt to address these challenges, they overlook the interference of event-unrelated sentences during event detection and neglect the mutual interference of different event roles during argument extraction.

Document-level Event Extraction Event Detection +1

DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event Extraction

no code implementations • 16 Oct 2023 • Gang Zhao, Xiaocheng Gong, Xinjie Yang, Guanting Dong, Shudong Lu, Si Li

Most current Event Extraction (EE) methods focus on the high-resource scenario, which requires a large amount of annotated data and can hardly be applied to low-resource domains.

Domain Adaptation Event Extraction +2