Chinese Address Research Articles

Recognition Method of New Address Elements in Chinese Address Matching Based on Deep Learning

Location services based on address matching play an important role in people’s daily lives. However, with the rapid development of cities, new addresses are constantly emerging. Due to the untimely updating of word segmentation dictionaries and address databases, the accuracy of address segmentation and the certainty of address matching face severe challenges. Therefore, a new address element recognition method for address matching is proposed. The method first uses the bidirectional encoder representations from transformers (BERT) model to learn the contextual information and address model features. Second, the conditional random field (CRF) is used to model the constraint relationships among the tags. Finally, a new address element is recognized according to the tag, and the new address element is put into the word segmentation dictionary. The spatial information is assigned to it, and it is put into the address database. Different sequence tagging models and different vector representations of addresses are used for comparative evaluation. The experimental results show that the method introduced in this paper achieves the maximum generalization ability, its F1 score is 0.78, and the F1 score on the testing dataset also achieves a high value (0.95).

Extracting Chinese geographic data from Baidu Map API

In this article, we describe the two new commands cngcode and cnaddress, which can be used to link Chinese addresses to locations defined by their longitudes and latitudes through Baidu Map API v3.0 ( http://api.map.baidu.com ), an online map and navigation system widely used in China. cngcode transfers Chinese addresses to locations, whereas cnaddress does the opposite. These two commands make it easier with Stata to deal with addresses and locations in China.

A Coarse-to-Fine Model for Geolocating Chinese Addresses

Address geolocation aims to associate address texts to the geographic locations. In China, due to the increasing demand for LBS applications such as take-out services and express delivery, automatically geolocating the unstructured address information is the key issue that needs to be solved first. Recently, a few approaches have been proposed to automate the address geolocation by directly predicting geographic coordinates. However, such point-based methods ignore the hierarchy information in addresses which may cause poor geolocation performance. In this paper, we propose a hierarchical region-based approach for geolocating Chinese addresses. We model the address geolocation as a Sequence-to-Sequence (Seq2Seq) learning task, that is, the input sequence is a textual address, and the output sequence is a GeoSOT grid code which exactly represents multi-level regions covered by the address. A novel coarse-to-fine model, which combines BERT and LSTM, is designed to learn the task. The experimental results demonstrate that our model correctly understands the Chinese addresses and achieves the highest geolocation accuracy among all the baselines.

Bidirectional Gated Recurrent Unit Neural Network for Chinese Address Element Segmentation

Chinese address element segmentation is a basic and key step in geocoding technology, and the segmentation results directly affect the accuracy and certainty of geocoding. However, due to the lack of obvious word boundaries in Chinese text, the grammatical and semantic features of Chinese text are complicated. Coupled with the diversity and complexity in Chinese address expressions, the segmentation of Chinese address elements is a substantial challenge. Therefore, this paper proposes a method of Chinese address element segmentation based on a bidirectional gated recurrent unit (Bi-GRU) neural network. This method uses the Bi-GRU neural network to generate tag features based on Chinese word segmentation and then uses the Viterbi algorithm to perform tag inference to achieve the segmentation of Chinese address elements. The neural network model is trained and verified based on the point of interest (POI) address data and partial directory data from the Baidu map of Beijing. The results show that the method is superior to previous neural network models in terms of segmentation performance and efficiency.

China’s scholarship shows atypical referencing patterns

China has greatly increased the number of published works indexed in the Web of Science since 1980. This corpus of scholarship allows analysis of the creativity or innovation of that contribution, where creativity is indicated by deep conventionality and high novelty. A test is applied to analyze reference pairs in articles to search for unexpected referencing combinations at the journal–journal level. The method has shown that atypical reference pairs occur in more highly cited articles. Using articles with at least one Chinese address as indexed in Web of Science for the publication year 2007, we tagged articles based on the conventionality and novelty of the reference pairs, seeking, in particular, those articles that reveal atypicality. This atypical set of articles represented 8% of all Chinese articles, compared to the world level of 7% in 2005. China’s atypical work is also more highly cited than a similar set of records at the world level for the years 1980–2000. The findings suggest that China has advanced in its goals of establishing itself as a full participant in global science and technology.

China’s Scholarship Shows Atypical Referencing Patterns

China has greatly increased the number of published works indexed in the Web of Science since 1980. This corpus of scholarship allows analysis of the creativity or innovation of that contribution, where creativity is indicated by deep conventionality and high novelty. A test is applied to analyze reference pairs in articles to search for unexpected referencing combinations at the journal-journal level. The method has shown that atypical reference pairs occur in more highly cited articles. Using articles with at least one Chinese address as indexed in Web of Science for the publication year 2007, we tagged articles based on the conventionality and novelty of the reference pairs, seeking, in particular, those articles that reveal atypicality. This atypical set of articles represented 8% of all Chinese articles, compared to the world level of 7% in 2005. China’s atypical work is also more highly cited than a similar set of records at the world level for the years 1980 to 2000. The findings suggest that China has advanced in its goals of establishing itself as a full participant in global science and technology.

Weighted Geocoding Method Based on Chinese Word Segmentation and Its Application to Spatial Positioning of COVID-19 Epidemic Prevention and Control

Locating the coronavirus disease 2019 (COVID-19)cases in the accurate place is important in epidemic prevention and control. Geocoding is an effective method to achieve information space positioning with address description. The English based geocoding methodology is not suitable for Chinese address. Composition and positioning methods of Chinese address are discussed. According to the characteristics of high complexity and diversity of Chinese address, a Chinese word segmentation weighted address matching algorithm considering a variety of semantics is designed, including the same pronunciation but different Chinese word address, abbreviation and alias of Chinese address, different description of the same address. And the matching accuracy and efficiency of the algorithm are tested by using the COVID-19 cases' addresses in Wuhan. The result indicates the algorithm is efficient, accurate, and intelligent, which can realize the efficient location of the COVID-19 cases address, and provide accurate spatial location information for epidemic prevention and control by quickly positioning of the COVID-19 cases.

GSAM: A deep neural network model for extracting computational representations of Chinese addresses fused with geospatial feature

Addresses are one of the most important geographical reference systems in natural languages. In China, due to the relatively backward address planning, there are a large number of non-standard addresses. This kind of unstructured text makes the management and application of Chinese addresses much more difficult. However, by extracting the computational representations of addresses, it can be structured and its related applications can be extended more conveniently. Therefore, this paper utilizes a deep neural language model from natural language processing (NLP) to automatically extract computational representations through an unsupervised address language model (ALM), which is trained in an unsupervised way and is suitable for a large-scale address corpus. We propose a solution to fuse addresses and geospatial features and construct a geospatial-semantic address model (GSAM) that supports a variety of downstream tasks. Our proposed GSAM constructing process consists of three phases. First, we build an ALM using bidirectional encoder representations from Transformers (BERT) to learn the addresses' semantic representations. Then, the fusion clustering results of the semantic and geospatial information are obtained by a high-dimensional clustering algorithm. Finally, we construct the GSAM based on the fused clustering results using novel fine-tuning techniques. Furthermore, we apply the extracted computational representation from GSAM to the address location prediction task. The experimental results indicate that the target task accuracy of the ALM is 90.79%, and the result of semantic geospatial fusion clustering strongly correlates with fine-grained urban neighbourhood area division. The GSAM can accurately identify clustering labels and the values of evaluation metrics are all above 0.96. We also demonstrate that our model outperforms purely ALM-based and word2vec-based models by address location prediction task.

Spatial pattern analysis of address quality: A study on the impact of rapid urban expansion in China

Standard address data are essential geographical information that play an important role in urban management. However, due to the complex structures of Chinese addresses, poor address quality has long been a problem in China. Although several measures were established to improve the address quality, nonstandard address data are still common in new urban areas. To investigate the potential causes of the geographical disparities in address quality, in this paper, we hypothesize that the sprawling urban form caused by rapid urban expansion in China has hindered the generation of standard addresses in new urban areas. To test this hypothesis, the spatial pattern of address quality in Shenzhen, China, is analyzed, and the potential causal paths relating urban expansion, urban form, and address quality are examined using structural equation modeling. The results indicate poorer address quality in new urban areas in Shenzhen. Rapid urban expansion has an indirect negative relation with the address quality. In addition, both road compactness and land use compactness have a direct positive effect on address quality, but the latter is insignificant. In this case, to facilitate improvements in address quality, a plan with dense and small blocks is suggested in the planning of new urban areas.

Bigger Than You Thought: China's Contribution to Scientific Publications and Its Impact on the Global Economy

AbstractChina's advance to the forefront of scientific research is one of the 21st century's most surprising developments, with implications for a world where knowledge is arguably “the one ring that rules them all.” This paper provides new estimates of China's contribution to global science that far exceed estimates based on the proportion of papers with Chinese addresses in databases of international journals. Address‐based measures ignore articles written by Chinese researchers with non‐Chinese addresses and articles in Chinese language journals not indexed in those databases. Taking account of these contributions, we attribute 36 percent of 2016 global scientific articles to China. Taking account of increased citations to Chinese‐addressed articles relative to the global average as well, we attribute 37 percent of global citations to scientific articles published in 2013 to China. With shares of articles and citations more than twice its share of global population or GDP, China has achieved a comparative advantage in knowledge that has implications for the division of labor and trade among countries and for the direction of research and of technological and economic development worldwide.

The Influences of Cultural Different Politeness on the use of address terms in Chinese and in English Discourse

Address terms are words used to address others and oneself. It plays an important role in discourse, for it indicates the discourse afterward as well as gives the counterpart a good impression by using the appropriate forms. The correct and appropriate use of address terms closely relates to culture. There is a certain gap between Chinese culture and western culture, which contributes a great deal to Chinese and English languages. However, a polite utterance with appropriate addressing always facilitates successful communication in all cultures. Therefore, in order to make a smooth communication in the discourse, usually starting with addresses, it is quite significant to understand politeness in the use of address terms. Based on cultural different politeness theories in both China and west, .this paper analyzes the different use of Chinese and English address in discourse under different circumstances. Only through fully comprehending the cultural featured politeness can address terms be used appropriately and serve successful communication.

Chinese address standardisation via hybrid approach combining statistical and rule-based methods

This paper is derived from the research project of cleansing customer address data for the State Grid Corporation of China (SGCC), which is the largest electric utility company in the world and was ranked the 2nd in the 2016 Fortune Global 500. Address standardisation involves development of a standard address format for data integration, de-duplication, auto address correction/completion, and is widely considered as a very challenging data cleansing task. Address standardisation is critical for routine business tasks, customer relationship management, business intelligence for customer-oriented cooperates, and others. Address standardisation is particularly difficult for the Chinese language. The underlying reasons include: 1) the current address standard placed in China is only realised at the city/town level; 2) due to a number of reasons, many hand-written addresses are incomplete or contain errors; 3) it is difficult to process the Chinese language in a machine fashion due to the language. characteristics. To tackle challenges, we propose a hybrid approach combining both statistical and rule-based methods, which are the two mainstream address standardisation approaches. Our hybrid approach utilises the merits of the both methods and can complete the address standardisation task with a little human efforts and computational time, while achieving high accuracy.

面向中文地址的复杂数据治理体系

面向中文地址的复杂数据治理体系

Chinese address standardisation via hybrid approach combining statistical and rule-based methods

This paper is derived from the research project of cleansing customer address data for the State Grid Corporation of China (SGCC), which is the largest electric utility company in the world and was ranked the 2nd in the 2016 Fortune Global 500. Address standardisation involves development of a standard address format for data integration, de-duplication, auto address correction/completion, and is widely considered as a very challenging data cleansing task. Address standardisation is critical for routine business tasks, customer relationship management, business intelligence for customer-oriented cooperates, and others. Address standardisation is particularly difficult for the Chinese language. The underlying reasons include: 1) the current address standard placed in China is only realised at the city/town level; 2) due to a number of reasons, many hand-written addresses are incomplete or contain errors; 3) it is difficult to process the Chinese language in a machine fashion due to the language. characteristics. To tackle challenges, we propose a hybrid approach combining both statistical and rule-based methods, which are the two mainstream address standardisation approaches. Our hybrid approach utilises the merits of the both methods and can complete the address standardisation task with a little human efforts and computational time, while achieving high accuracy.

Research on Chinese Address Resolution Model Based on Conditional Random Field

In this paper, a Chinese address resolution method based on Conditional Random Fields is proposed. In this method, the address resolution is divided into the address segmentation and the address component annotation issues, and moreover, the segmentation is combined with the address component annotation to form the annotated data set of output sequences. Meanwhile, taking a full consideration of the composition and use habits of Chinese address, the helpful characteristics to address resolution is set. Then, the address corpus and the corresponding characteristic template are constructed, and the conditional model which is suitable for Chinese non-standard address is obtained with model training of conditional random fields. In the end, the performance test is conducted on the conditional model of Chinese address on test set gained through training with experiments. Results show that the annotation accuracy of conditional random fields conforms to the requirements of address matching basically, and the accuracy is over 80%, with a certain practical value.

A Quantitative analysis of Korean and Chinese address forms of employee in the restaurant based on comparisons between the survey results of the existing studies and the textbooks of the two languages : Focusing on Yeogi/Jeogi-yo in Korean and Shuai-Ge/Me

A Quantitative analysis of Korean and Chinese address forms of employee in the restaurant based on comparisons between the survey results of the existing studies and the textbooks of the two languages : Focusing on Yeogi/Jeogi-yo in Korean and Shuai-Ge/Me

A hybrid method for Chinese address segmentation

ABSTRACTChinese address segmentation is a serious challenge in geographic information system geocoding. Most previous studies have relied on predefined gazetteers without considering the information contained by a raw address corpus. In this paper, a hybrid method employing both rule-based and statistical methods is proposed for Chinese address segmentation without a predefined gazetteer. This approach utilizes statistical methods to extract address information from a raw address corpus and a rule-based method to segment Chinese addresses. Two typical statistical methods and their combinations with rule-based methods are compared with the hybrid method in an experiment involving approximately 460,000 address items in Shenzhen City, China. The experimental results indicate that the proposed method achieves an F-score of over 0.8, which is better than those of existing methods, thus validating the proposed method.

Current address behaviour in China

The way in which people address each other is crucial for expressing interpersonal relationships and is closely linked with cultural values. Address terms are pragmatically important, especially in languages that do not express sociopragmatic values through pronouns such as Chinese. Due to the rapid change of sociocultural values and the advancement of globalisation and new technologies, many Chinese address terms are falling out of use, and new terms are emerging and prevailing in people’s use. However, many landmark studies on Chinese address terms are no longer up-to-date. This article investigates the current use of address terms in Mainland China. Four categories of Chinese address terms are analysed: obsolete terms with restricted uses, revived negative politeness forms with semantic shifts, emergent new address terms, and address terms adopted from online communication. The article then discusses factors that may influence people selecting address terms and factors affecting the changes of address terms in Chinese.

Using an Optimized Chinese Address Matching Method to Develop a Geocoding Service: A Case Study of Shenzhen, China

With the coming era of big data and the rapid development and widespread applications of Geographical Information Systems (GISs), geocoding technology is playing an increasingly important role in bridging the gap between non-spatial data resources and spatial data in various fields. However, Chinese geocoding faces great challenges because of the complexity of the address string format in Chinese, which contains no delimiters between Chinese words, and the poor address management resulting from the existence of multiple address authorities spread among different governmental agencies. This paper presents a geocoding service based on an optimized Chinese address matching method, including address modeling, address standardization and address matching. The address model focuses on the spatial semantics of each address element, and the address standardization process is based on an address tree model. A geocoding service application is implemented in practice using a large quantity of data from Shenzhen Municipality. More than 1,460,000 data records were used to test the geocoding service, and good matching rates were achieved with good adaptability and intelligence.

Recognition of handwritten Chinese address with writing variations

Handwritten Chinese address recognition is a challenging task, not only because of the large quantity of Chinese characters and unconstraint of handwriting, but also due to irregularities of various address formats. The existing techniques generally solve the problem by transforming the address database to a large scale character-level-tree (CLT) and then utilizing the nodes of the generated CLT to match with the candidate patterns. However, the CLT is unable to cover all the variations of address formats. A more compact tree is proposed in this paper to cover the variations of address formats as many and complete as possible by building the structure tree at word level. Specifically, the segment candidate patterns are firstly recognized by a character classifier, then are mapped to candidate address words by matching with the proposed word-level-tree (WLT) address database. Finally, the address recognition result is obtained in the path matching phase by summing the scores of candidate address words in each match path. The proposed scheme was tested with real mail address images captured by an automatic letter sorting machine. Experimental results have demonstrated that the performance of the proposed WLT based method outperforms the four benchmarking methods.