A Question and Answering Service of Typhoon Disasters Based on the T5 Large Language Model

Bibliographic Data

ID22031391
AuthorsYongqi Xia (0009-0005-0024-769X, Nanjing University of Posts and Telecommunications), Yi Huang (0000-0001-5702-0705, Nanjing Normal University, corresponding author), Qianqian Qiu (0000-0002-3841-6947, Nanjing Surveying and Mapping Research Institute (China)), Xueying Zhang (0000-0003-2731-829X, Nanjing Normal University), Lizhi Miao (0000-0001-8768-4502, Nanjing University of Posts and Telecommunications), Yixiang Chen (0009-0003-6686-3634, Nanjing University of Posts and Telecommunications)
Year2024
Volume13
Issue5
Pages165
Publication date2024-05-14
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueISPRS International Journal of Geo-Information (JOURNAL)
Journal identifiersISSN: 2220-9964 • E-ISSN: 2220-9964
PublisherMDPI AG (PUBLISHER • IT)
DOI10.3390/ijgi13050165
OpenAlexW4396888196
LanguageEN
Citations received2
References cited47

A typhoon disaster is a common meteorological disaster that seriously impacts natural ecology, social economy, and even human sustainable development. It is crucial to access the typhoon disaster information, and the corresponding disaster prevention and reduction strategies. However, traditional question and answering (Q&A) methods exhibit shortcomings like low information retrieval efficiency and poor interactivity. This makes it difficult to satisfy users’ demands for obtaining accurate information. Consequently, this work proposes a typhoon disaster knowledge Q&A approach based on LLM (T5). This method integrates two technical paradigms of domain fine-tuning and retrieval-augmented generation (RAG) to optimize user interaction experience and improve the precision of disaster information retrieval. The process specifically includes the following steps. First, this study selects information about typhoon disasters from open-source databases, such as Baidu Encyclopedia and Wikipedia. Utilizing techniques such as slicing and masked language modeling, we generate a training set and 2204 Q&A pairs specifically focused on typhoon disaster knowledge. Second, we continuously pretrain the T5 model using the training set. This process involves encoding typhoon knowledge as parameters in the neural network’s weights and fine-tuning the pretrained model with Q&A pairs to adapt the T5 model for downstream Q&A tasks. Third, when responding to user queries, we retrieve passages from external knowledge bases semantically similar to the queries to enhance the prompts. This action further improves the response quality of the fine-tuned model. Finally, we evaluate the constructed typhoon agent (Typhoon-T5) using different similarity-matching approaches. Furthermore, the method proposed in this work lays the foundation for the cross-integration of large language models with disaster information. It is expected to promote the further development of GeoAI

Database · Information retrieval · Interactivity · Meteorology · Ontology · Typhoon · World Wide Web · Computer Science · Disaster Management and Resilience · Tropical and Extratropical Cyclones Research · Artificial Intelligence

Tools

Open DOIOpen Access