A DeBERTa-Based Semantic Conversion Model for Spatiotemporal Questions in Natural Language

To address current issues in natural language spatiotemporal queries, including insufficient question semantic understanding, incomplete semantic information extraction, and inaccurate intent recognition, this paper proposes NL2Cypher, a DeBERTa (Decoding-enhanced BERT with disentangled attention)-b...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenjuan Lu, Dongping Ming, Xi Mao, Jizhou Wang, Zhanjie Zhao, Yao Cheng
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/3/1073
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199345914183680
author Wenjuan Lu
Dongping Ming
Xi Mao
Jizhou Wang
Zhanjie Zhao
Yao Cheng
author_facet Wenjuan Lu
Dongping Ming
Xi Mao
Jizhou Wang
Zhanjie Zhao
Yao Cheng
author_sort Wenjuan Lu
collection DOAJ
description To address current issues in natural language spatiotemporal queries, including insufficient question semantic understanding, incomplete semantic information extraction, and inaccurate intent recognition, this paper proposes NL2Cypher, a DeBERTa (Decoding-enhanced BERT with disentangled attention)-based natural language spatiotemporal question semantic conversion model. The model first performs semantic encoding on natural language spatiotemporal questions, extracts pre-trained features based on the DeBERTa model, inputs feature vector sequences into BiGRU (Bidirectional Gated Recurrent Unit) to learn text features, and finally obtains globally optimal label sequences through a CRF (Conditional Random Field) layer. Then, based on the encoding results, it performs classification and semantic parsing of spatiotemporal questions to achieve question intent recognition and conversion to Cypher query language. The experimental results show that the proposed DeBERTa-based conversion model NL2Cypher can accurately achieve semantic information extraction and intent understanding in both simple and compound queries when using Chinese corpus, reaching an F1 score of 92.69%, with significant accuracy improvement compared to other models. The conversion accuracy from spatiotemporal questions to query language reaches 88% on the training set and 92% on the test set. The proposed model can quickly and accurately query spatiotemporal data using natural language questions. The research results provide new tools and perspectives for subsequent knowledge graph construction and intelligent question answering, effectively promoting the development of geographic information towards intelligent services.
format Article
id doaj-art-a7a982ea699a46c18877bf138f114bdb
institution OA Journals
issn 2076-3417
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-a7a982ea699a46c18877bf138f114bdb2025-08-20T02:12:38ZengMDPI AGApplied Sciences2076-34172025-01-01153107310.3390/app15031073A DeBERTa-Based Semantic Conversion Model for Spatiotemporal Questions in Natural LanguageWenjuan Lu0Dongping Ming1Xi Mao2Jizhou Wang3Zhanjie Zhao4Yao Cheng5School of Information Engineering, China University of Geosciences Beijing, Beijing 100083, ChinaSchool of Information Engineering, China University of Geosciences Beijing, Beijing 100083, ChinaChinese Academy of Surveying and Mapping, Beijing 100036, ChinaChinese Academy of Surveying and Mapping, Beijing 100036, ChinaChinese Academy of Surveying and Mapping, Beijing 100036, ChinaChinese Academy of Surveying and Mapping, Beijing 100036, ChinaTo address current issues in natural language spatiotemporal queries, including insufficient question semantic understanding, incomplete semantic information extraction, and inaccurate intent recognition, this paper proposes NL2Cypher, a DeBERTa (Decoding-enhanced BERT with disentangled attention)-based natural language spatiotemporal question semantic conversion model. The model first performs semantic encoding on natural language spatiotemporal questions, extracts pre-trained features based on the DeBERTa model, inputs feature vector sequences into BiGRU (Bidirectional Gated Recurrent Unit) to learn text features, and finally obtains globally optimal label sequences through a CRF (Conditional Random Field) layer. Then, based on the encoding results, it performs classification and semantic parsing of spatiotemporal questions to achieve question intent recognition and conversion to Cypher query language. The experimental results show that the proposed DeBERTa-based conversion model NL2Cypher can accurately achieve semantic information extraction and intent understanding in both simple and compound queries when using Chinese corpus, reaching an F1 score of 92.69%, with significant accuracy improvement compared to other models. The conversion accuracy from spatiotemporal questions to query language reaches 88% on the training set and 92% on the test set. The proposed model can quickly and accurately query spatiotemporal data using natural language questions. The research results provide new tools and perspectives for subsequent knowledge graph construction and intelligent question answering, effectively promoting the development of geographic information towards intelligent services.https://www.mdpi.com/2076-3417/15/3/1073semantic encodingnatural language spatiotemporal questionssemantic understandingDeBERTa
spellingShingle Wenjuan Lu
Dongping Ming
Xi Mao
Jizhou Wang
Zhanjie Zhao
Yao Cheng
A DeBERTa-Based Semantic Conversion Model for Spatiotemporal Questions in Natural Language
Applied Sciences
semantic encoding
natural language spatiotemporal questions
semantic understanding
DeBERTa
title A DeBERTa-Based Semantic Conversion Model for Spatiotemporal Questions in Natural Language
title_full A DeBERTa-Based Semantic Conversion Model for Spatiotemporal Questions in Natural Language
title_fullStr A DeBERTa-Based Semantic Conversion Model for Spatiotemporal Questions in Natural Language
title_full_unstemmed A DeBERTa-Based Semantic Conversion Model for Spatiotemporal Questions in Natural Language
title_short A DeBERTa-Based Semantic Conversion Model for Spatiotemporal Questions in Natural Language
title_sort deberta based semantic conversion model for spatiotemporal questions in natural language
topic semantic encoding
natural language spatiotemporal questions
semantic understanding
DeBERTa
url https://www.mdpi.com/2076-3417/15/3/1073
work_keys_str_mv AT wenjuanlu adebertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage
AT dongpingming adebertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage
AT ximao adebertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage
AT jizhouwang adebertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage
AT zhanjiezhao adebertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage
AT yaocheng adebertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage
AT wenjuanlu debertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage
AT dongpingming debertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage
AT ximao debertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage
AT jizhouwang debertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage
AT zhanjiezhao debertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage
AT yaocheng debertabasedsemanticconversionmodelforspatiotemporalquestionsinnaturallanguage