Chinese toponym recognition with variant neural structures from social media messages based on BERT methods

Abstract

Many natural language tasks related to geographic information retrieval (GIR) require toponym recognition, and identifying Chinese toponyms from social media messages to share real-time information is a critical problem for many practical applications, such as natural disaster response and geolocating. In this article, we focused on toponym recognition from social media messages in Chinese. While existing off-the-shelf Chinese named entity recognition (NER) tools could be applied to identify toponyms, these approaches cannot address a variety of language irregularities taken from social media messages, including location name abbreviations, informal sentence structures and combination toponyms. We present a deep neural network named BERT-BiLSTM-CRF, which extends a basic bidirectional recurrent neural network model (BiLSTM) with the pretraining bidirectional encoder representation from transformers (BERT) representation to handle the toponym recognition task in Chinese text. Using three datasets taken from lists of alternative location names, the experimental results showed that the proposed model can significantly outperform previous Chinese NER models/algorithms and a set of state-of-the-art deep learning models.

ChineseCTRE: A Model for Geographical Named Entity Recognition and Correction Based on Deep Neural Networks and the BERT Model

“…However, directly applying BERT to geographic named entity recognition may ignore the interlabel constraint relationship between label sequences, which can significantly affect the model's performance in the task. To address this, Ma et al proposed a BERT-BiLSTM-CRF deep neural network architecture for Chinese text geotagging tasks [33]. Qiu et al proposed a ChineseTR architecture based on weakly supervised BERT + BiLSTM + CRF for Chinese geotagging and trained the Chinese geotagging model on a training dataset generated from the People's Daily corpus [34].…”

A Study on Toponymic Entity Recognition Based on Pre-Trained Models Fused with Local Features for Genglubu in the South China Sea

“…The experimental results are excellent [22]. Ma K et al proposed a neural network model based on BERT-BiLSTM-CRF for Chinese place name entity recognition, which performs well on MSRA, GeoTR-20, and other datasets [23]. Ziniu W et al proposed a hybrid neural network model based on BERT to address the problems of not fully considering the context and ignoring the local features in the NER task by combining the BiLSTM and IDCNN models to extract the features, which resulted in a 4.79% improvement in the F1 value compared with the baseline model on the CLUENER dataset [24].…”

A Sustainable Way Forward: Systematic Review of Transformer Technology in Social-Media-Based Disaster Analytics

“…Studies in this category try to extract location descriptions and identify geographical references from disaster-related social media messages [49][50][51]. Table 7 summarizes the categorization of location identification and description extraction.…”

“…The detailed review for each paper is provided in Appendix A, Table A4. BERT with BiLSTM-CRF achieves high accuracy in recognizing toponyms, aiding location identification in disaster communications [49,51]. However, its practical application lacks direct examples in disaster management contexts.…”