Csmner
A Toponym Entity Recognition Model for Chinese Social Media
Bibliographic Data
| ID | 22032632 |
|---|---|
| Authors | Yuyang Qi (0009-0001-7836-1186, PLA Information Engineering University), Renjian Zhai (PLA Information Engineering University, corresponding author), Fang Wu (0000-0002-8436-7293, PLA Information Engineering University), Jichong Yin (0000-0001-9690-6373, PLA Information Engineering University), Xianyong Gong (0000-0002-6184-1300, PLA Information Engineering University), Li Zhu (0000-0003-0179-6496, PLA Information Engineering University), Haikun Yu (Henan Institute of Geological Survey) |
| Year | 2024 |
| Volume | 13 |
| Issue | 9 |
| Pages | 311 |
| Publication date | 2024-08-29 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | ISPRS International Journal of Geo-Information (JOURNAL) |
| Journal identifiers | ISSN: 2220-9964 • E-ISSN: 2220-9964 |
| Publisher | MDPI AG (PUBLISHER • IT) |
| DOI | 10.3390/ijgi13090311 |
| OpenAlex | W4401992084 |
| Language | EN |
| Citations received | 2 |
| References cited | 34 |
In the era of information explosion, Chinese social media has become a repository for massive geographic information; however, its unique unstructured nature and diverse expressions are challenging to toponym entity recognition. To address this problem, we propose a Chinese social media named entity recognition (CSMNER) model to improve the accuracy and robustness of toponym recognition in Chinese social media texts. By combining the BERT (Bidirectional Encoder Representations from Transformers) pre-trained model with an improved IDCNN-BiLSTM-CRF (Iterated Dilated Convolutional Neural Network- Bidirectional Long Short-Term Memory- Conditional Random Field) architecture, this study innovatively incorporates a boundary extension module to effectively extract the local boundary features and contextual semantic features of the toponym, successfully addressing the recognition challenges posed by noise interference and language expression variability. To verify the effectiveness of the model, experiments were carried out on three datasets: WeiboNER, MSRA, and the Chinese social named entity recognition (CSNER) dataset, a self-built named entity recognition dataset. Compared with the existing models, CSMNER achieves significant performance improvement in toponym recognition tasks
Internet privacy · Social media · World Wide Web · Authorship Attribution and Profiling · Computer Science · Natural Language Processing Techniques · Topic Modeling
| Citations per year | 2 |
|---|---|
| Citation span | 2026 - 2026 (1) |
| Highly cited | No |