Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Yibo, Parolin, Erick Skorupa, Khan, Latifur, Brandt, Patrick T., Osorio, Javier, D'Orazio, Vito J.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910473471918080
author Hu, Yibo
Parolin, Erick Skorupa
Khan, Latifur
Brandt, Patrick T.
Osorio, Javier
D'Orazio, Vito J.
author_facet Hu, Yibo
Parolin, Erick Skorupa
Khan, Latifur
Brandt, Patrick T.
Osorio, Javier
D'Orazio, Vito J.
contents Is it possible accurately classify political relations within evolving event ontologies without extensive annotations? This study investigates zero-shot learning methods that use expert knowledge from existing annotation codebook, and evaluates the performance of advanced ChatGPT (GPT-3.5/4) and a natural language inference (NLI)-based model called ZSP. ChatGPT uses codebook's labeled 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, and adaptability to schema changes. The experiments reveal ChatGPT's strengths and limitations, and crucially show ZSP's outperformance of dictionary-based methods and its competitive edge over some supervised models. These findings affirm the value of ZSP for validating event records and advancing ontology development. Our study underscores the efficacy of leveraging transfer learning and existing domain expertise to enhance research efficiency and scalability.
format Preprint
id arxiv_https___arxiv_org_abs_2308_07876
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification
Hu, Yibo
Parolin, Erick Skorupa
Khan, Latifur
Brandt, Patrick T.
Osorio, Javier
D'Orazio, Vito J.
Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
Is it possible accurately classify political relations within evolving event ontologies without extensive annotations? This study investigates zero-shot learning methods that use expert knowledge from existing annotation codebook, and evaluates the performance of advanced ChatGPT (GPT-3.5/4) and a natural language inference (NLI)-based model called ZSP. ChatGPT uses codebook's labeled 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, and adaptability to schema changes. The experiments reveal ChatGPT's strengths and limitations, and crucially show ZSP's outperformance of dictionary-based methods and its competitive edge over some supervised models. These findings affirm the value of ZSP for validating event records and advancing ontology development. Our study underscores the efficacy of leveraging transfer learning and existing domain expertise to enhance research efficiency and scalability.
title Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification
topic Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2308.07876