TourismNER: A Tourism Named Entity Recognition method based on entity boundary joint prediction

Tourism named entity recognition is indispensable in tourism information extraction, and plays a crucial role in constructing tourism knowledge map and enhancing tourism knowledge quiz system. The difficulty of tourism named entity recognition lies in its complex nested structure, and the lengthy en...

Full description

Saved in:
Bibliographic Details
Main Authors: Kai Gao, Jiahao Zhou, Yunxian Chi, Yimin Wen
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Intelligent Systems with Applications
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667305325000018
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849766266769768448
author Kai Gao
Jiahao Zhou
Yunxian Chi
Yimin Wen
author_facet Kai Gao
Jiahao Zhou
Yunxian Chi
Yimin Wen
author_sort Kai Gao
collection DOAJ
description Tourism named entity recognition is indispensable in tourism information extraction, and plays a crucial role in constructing tourism knowledge map and enhancing tourism knowledge quiz system. The difficulty of tourism named entity recognition lies in its complex nested structure, and the lengthy entity naming length. To address these existing problems, we propose a tourism named entity recognition model that jointly predicts entity boundaries, adopting a training strategy of data preprocessing to enhance the model’s ability for tourism named entity boundary recognition, while our model introduces a pre-trained Bert model as well as BiLSTM coding to enhance the representation of the model’s contexts, and uses a combined predictor of Biaffine and MLP to enhance the model’s recognition performance for boundaries, as well as introducing label smoothing cross entropy to smooth the target labels during the training process. Experiments are conducted on three datasets with different granularities. From the analysis of the experimental results, it can be seen that the named entity recognition method achieves higher accuracy and F1 value compared with the optimal baseline model, and also proves the effectiveness and generality of the modeling method proposed in this paper.
format Article
id doaj-art-a94df3a040f647c18f0ae505e172b1ad
institution DOAJ
issn 2667-3053
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Intelligent Systems with Applications
spelling doaj-art-a94df3a040f647c18f0ae505e172b1ad2025-08-20T03:04:38ZengElsevierIntelligent Systems with Applications2667-30532025-03-012520047510.1016/j.iswa.2025.200475TourismNER: A Tourism Named Entity Recognition method based on entity boundary joint predictionKai Gao0Jiahao Zhou1Yunxian Chi2Yimin Wen3School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, 050018, ChinaSchool of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, 050018, China; Guangxi Key Laboratory of Culture and Tourism Smart Technology, Guilin Tourism University, Guilin, 541006, ChinaSchool of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, 050018, ChinaGuangxi Key Laboratory of Culture and Tourism Smart Technology, Guilin Tourism University, Guilin, 541006, China; Guangxi Key Laboratory of Image and Graphic intelligent processing, Guilin University of Electronic Technology, Guilin, 541004, China; Corresponding author.Tourism named entity recognition is indispensable in tourism information extraction, and plays a crucial role in constructing tourism knowledge map and enhancing tourism knowledge quiz system. The difficulty of tourism named entity recognition lies in its complex nested structure, and the lengthy entity naming length. To address these existing problems, we propose a tourism named entity recognition model that jointly predicts entity boundaries, adopting a training strategy of data preprocessing to enhance the model’s ability for tourism named entity boundary recognition, while our model introduces a pre-trained Bert model as well as BiLSTM coding to enhance the representation of the model’s contexts, and uses a combined predictor of Biaffine and MLP to enhance the model’s recognition performance for boundaries, as well as introducing label smoothing cross entropy to smooth the target labels during the training process. Experiments are conducted on three datasets with different granularities. From the analysis of the experimental results, it can be seen that the named entity recognition method achieves higher accuracy and F1 value compared with the optimal baseline model, and also proves the effectiveness and generality of the modeling method proposed in this paper.http://www.sciencedirect.com/science/article/pii/S2667305325000018Natural Language ProcessingTourism Named Entity RecognitionEntity boundary recognitionJoint prediction
spellingShingle Kai Gao
Jiahao Zhou
Yunxian Chi
Yimin Wen
TourismNER: A Tourism Named Entity Recognition method based on entity boundary joint prediction
Intelligent Systems with Applications
Natural Language Processing
Tourism Named Entity Recognition
Entity boundary recognition
Joint prediction
title TourismNER: A Tourism Named Entity Recognition method based on entity boundary joint prediction
title_full TourismNER: A Tourism Named Entity Recognition method based on entity boundary joint prediction
title_fullStr TourismNER: A Tourism Named Entity Recognition method based on entity boundary joint prediction
title_full_unstemmed TourismNER: A Tourism Named Entity Recognition method based on entity boundary joint prediction
title_short TourismNER: A Tourism Named Entity Recognition method based on entity boundary joint prediction
title_sort tourismner a tourism named entity recognition method based on entity boundary joint prediction
topic Natural Language Processing
Tourism Named Entity Recognition
Entity boundary recognition
Joint prediction
url http://www.sciencedirect.com/science/article/pii/S2667305325000018
work_keys_str_mv AT kaigao tourismneratourismnamedentityrecognitionmethodbasedonentityboundaryjointprediction
AT jiahaozhou tourismneratourismnamedentityrecognitionmethodbasedonentityboundaryjointprediction
AT yunxianchi tourismneratourismnamedentityrecognitionmethodbasedonentityboundaryjointprediction
AT yiminwen tourismneratourismnamedentityrecognitionmethodbasedonentityboundaryjointprediction