Schema Retrieval for Korean Geographic Knowledge Base Question Answering Using Few-Shot Prompting

Geographic Knowledge Base Question Answering (GeoKBQA) has garnered increasing attention for its ability to process complex geographic queries. This study focuses on schema retrieval, a critical step in GeoKBQA that involves extracting relevant schema items (classes, relations, and properties) to ge...

Full description

Saved in:
Bibliographic Details
Main Authors: Seokyong Lee, Kiyun Yu
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:https://www.mdpi.com/2220-9964/13/12/453
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846104376537513984
author Seokyong Lee
Kiyun Yu
author_facet Seokyong Lee
Kiyun Yu
author_sort Seokyong Lee
collection DOAJ
description Geographic Knowledge Base Question Answering (GeoKBQA) has garnered increasing attention for its ability to process complex geographic queries. This study focuses on schema retrieval, a critical step in GeoKBQA that involves extracting relevant schema items (classes, relations, and properties) to generate accurate operational queries. Current GeoKBQA studies primarily rely on rule-based approaches for schema retrieval. These predefine words or descriptions for each schema item. This rule-based method has three critical limitations: (1) poor generalization to undefined schema items, (2) failure to consider the semantic meaning of user queries, and (3) an inability to adapt to languages not used in the predefined step. In this study, we present a schema retrieval model by using few-shot prompting on GPT-4 Turbo to address these issues. Using the SKRE dataset, we searched for the best prompt in terms of enabling the model to handle Korean geographic questions across various generalization levels. Notably, this method outperformed fine-tuning in zero-shot scenarios, underscoring its adaptability to unseen data. To our knowledge, this is the first attempt to develop a schema retrieval model for GeoKBQA that purely utilizes a language model and is capable of processing Korean geographic questions.
format Article
id doaj-art-a808192b46c44ba6b6c3392a61acba80
institution Kabale University
issn 2220-9964
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj-art-a808192b46c44ba6b6c3392a61acba802024-12-27T14:30:09ZengMDPI AGISPRS International Journal of Geo-Information2220-99642024-12-01131245310.3390/ijgi13120453Schema Retrieval for Korean Geographic Knowledge Base Question Answering Using Few-Shot PromptingSeokyong Lee0Kiyun Yu1Department of Civil and Environmental Engineering, Seoul National University, Seoul 08826, Republic of KoreaDepartment of Civil and Environmental Engineering, Seoul National University, Seoul 08826, Republic of KoreaGeographic Knowledge Base Question Answering (GeoKBQA) has garnered increasing attention for its ability to process complex geographic queries. This study focuses on schema retrieval, a critical step in GeoKBQA that involves extracting relevant schema items (classes, relations, and properties) to generate accurate operational queries. Current GeoKBQA studies primarily rely on rule-based approaches for schema retrieval. These predefine words or descriptions for each schema item. This rule-based method has three critical limitations: (1) poor generalization to undefined schema items, (2) failure to consider the semantic meaning of user queries, and (3) an inability to adapt to languages not used in the predefined step. In this study, we present a schema retrieval model by using few-shot prompting on GPT-4 Turbo to address these issues. Using the SKRE dataset, we searched for the best prompt in terms of enabling the model to handle Korean geographic questions across various generalization levels. Notably, this method outperformed fine-tuning in zero-shot scenarios, underscoring its adaptability to unseen data. To our knowledge, this is the first attempt to develop a schema retrieval model for GeoKBQA that purely utilizes a language model and is capable of processing Korean geographic questions.https://www.mdpi.com/2220-9964/13/12/453GeoKBQAKBQAschema retrieval
spellingShingle Seokyong Lee
Kiyun Yu
Schema Retrieval for Korean Geographic Knowledge Base Question Answering Using Few-Shot Prompting
ISPRS International Journal of Geo-Information
GeoKBQA
KBQA
schema retrieval
title Schema Retrieval for Korean Geographic Knowledge Base Question Answering Using Few-Shot Prompting
title_full Schema Retrieval for Korean Geographic Knowledge Base Question Answering Using Few-Shot Prompting
title_fullStr Schema Retrieval for Korean Geographic Knowledge Base Question Answering Using Few-Shot Prompting
title_full_unstemmed Schema Retrieval for Korean Geographic Knowledge Base Question Answering Using Few-Shot Prompting
title_short Schema Retrieval for Korean Geographic Knowledge Base Question Answering Using Few-Shot Prompting
title_sort schema retrieval for korean geographic knowledge base question answering using few shot prompting
topic GeoKBQA
KBQA
schema retrieval
url https://www.mdpi.com/2220-9964/13/12/453
work_keys_str_mv AT seokyonglee schemaretrievalforkoreangeographicknowledgebasequestionansweringusingfewshotprompting
AT kiyunyu schemaretrievalforkoreangeographicknowledgebasequestionansweringusingfewshotprompting