Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models
This work addresses the problem of reducing human effort in data annotation for document-level relation extraction, which is incremental as it builds on existing LLM capabilities.
The authors tackled the challenge of automating annotation for document-level relation extraction by integrating a large language model with a natural language inference module to generate relation triples, resulting in an enhanced dataset called DocGNRE that excels in re-annotating long-tail relation types.
Document-level Relation Extraction (DocRE), which aims to extract relations from a long context, is a critical challenge in achieving fine-grained structural comprehension and generating interpretable document representations. Inspired by recent advances in in-context learning capabilities emergent from large language models (LLMs), such as ChatGPT, we aim to design an automated annotation method for DocRE with minimum human effort. Unfortunately, vanilla in-context learning is infeasible for document-level relation extraction due to the plenty of predefined fine-grained relation types and the uncontrolled generations of LLMs. To tackle this issue, we propose a method integrating a large language model (LLM) and a natural language inference (NLI) module to generate relation triples, thereby augmenting document-level relation datasets. We demonstrate the effectiveness of our approach by introducing an enhanced dataset known as DocGNRE, which excels in re-annotating numerous long-tail relation types. We are confident that our method holds the potential for broader applications in domain-specific relation type definitions and offers tangible benefits in advancing generalized language semantic comprehension.