Synthesizing Political Zero-Shot Relation Classification via Codebook Knowledge, NLI, and ChatGPT

arXiv:2308.07876v2 Announce Type: replace-cross
Abstract: Can we accurately classify political relations within evolving event ontologies without extensive annotations? Our study investigates zero-shot learning methods that utilize only expert knowledge from existing annotation codebook. We assess the performance of advanced ChatGPT (GPT-3.5/4) and a natural language inference (NLI)-based model called ZSP. ChatGPT uses codebooks' label summaries as prompts, whereas ZSP breaks down the classification task into context, event mode, and class disambiguation to refine task-specific hypotheses. This decomposition enhances interpretability, efficiency, …

abstract advanced annotation annotations arxiv chatgpt classification cs.ai cs.cl cs.ir cs.lg event expert gpt gpt-3 gpt-3.5 inference knowledge language natural natural language ontologies performance political relations study type via zero-shot