ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT

TL;DR

ChatIE leverages ChatGPT in a two-stage prompt-based framework to perform zero-shot information extraction across multiple tasks and languages, achieving competitive results without annotated data.

Contribution

This work introduces a novel multi-turn question-answering framework using ChatGPT for zero-shot IE, demonstrating its effectiveness across various tasks and datasets.

Findings

ChatIE surpasses some fully supervised models on several datasets.

It achieves high performance on entity-relation, NER, and event extraction tasks.

The approach works well across multiple languages and datasets.

Abstract

Zero-shot information extraction (IE) aims to build IE systems from the unannotated text. It is challenging due to involving little human intervention. Challenging but worthwhile, zero-shot IE reduces the time and effort that data labeling takes. Recent efforts on large language models (LLMs, e.g., GPT-3, ChatGPT) show promising performance on zero-shot settings, thus inspiring us to explore prompt-based methods. In this work, we ask whether strong IE models can be constructed by directly prompting LLMs. Specifically, we transform the zero-shot IE task into a multi-turn question-answering problem with a two-stage framework (ChatIE). With the power of ChatGPT, we extensively evaluate our framework on three IE tasks: entity-relation triple extract, named entity recognition, and event extraction. Empirical results on six datasets across two languages show that ChatIE achieves impressive performance and even surpasses some full-shot models on several datasets (e.g., NYT11-HRL). We believe that our work could shed light on building IE models with limited resources.