DeepAM: Deep Semantic Address Representation for Address Matching

Abstract

Address matching is a crucial task in various location-based businesses like take-out services and express delivery, which aims at identifying addresses referring to the same location in address databases. It is a challenging one due to various possible ways to express the address of a location, especially in Chinese. Traditional address matching approaches relying on string similarities and learning matching rules to identify addresses referring to the same location, could hardly solve the cases with redundant, incomplete or unusual expression of addresses. In this paper, we propose to map every address into a fixed-size vector in the same vector space using state-of-the-art deep sentence representation techniques and then measure the semantic similarity between addresses in this vector space. The attention mechanism is also applied to the model to highlight important features of addresses in their semantic representations. Last but not least, we novelly propose to get rich contexts for addresses from the web through web search engines, which could strongly enrich the semantic meaning of addresses that could be learned. Our empirical study conducted on two real-world address datasets demonstrates that our approach greatly improves both precision (up to 5%) and recall (up to 8%) of the state-of-the-art existing methods.

Automatic Identification of Addresses: A Systematic Literature Review

“…Figure 7 shows that the top 5 application domains consist of geographical information systems (GIS)/Census [27], POIs/Spatial Analysis [2], GIS/Urban Planning [9], GIS/Health Care [28], and Location Based Services [29]. Taking into account the average publication year (Figure 8), it is possible to observe that the most recent application domains consist of disease control (covid-19), location-based services, and GIS/census/urban planning, in which geocoding, with an increasing importance in people's daily lives, stands as a common feature.…”

“…Within the present literature review, several of the considered papers propose these types of methods, namely the ones by Santos et al [35], Lin et al [9], J. Liu et al [58], Shan et al [7,29], P. Li et al [69], and Chen et al [70]. To take into account contextual information both from previous and future tokens, by processing the sequence in two directions, bidirectional LSTM (BiLSTM) or GRU layers are also being employed in the great majority of these studies.…”

“…To take into account contextual information both from previous and future tokens, by processing the sequence in two directions, bidirectional LSTM (BiLSTM) or GRU layers are also being employed in the great majority of these studies. The best performing models further connect the encoder and decoder through an attention mechanism in order to assign higher weights to the most important features [7,9,29]. With a view to reduce overfitting and enhance the classification models' generalization abilities, a dropout regularization layer is also normally added [9,35,58].…”

“…The LM-LSTM-CRF+BP neural networks model proposed by J. Liu et al [58] achieves an accuracy and F1 score of 87%, compared with average scores of 70% by the benchmark methods (word2vec and edit distance). The address GCN method proposed by Shan et al [7] also presents better results, on both precision (up to 8%) and recall (up to 12%), than the existing methods, which include the DeepAM model previously proposed by the same author, based on an encoder-decoder architecture with two LSTM networks [29]. The Bi-GRU neural network proposed by P. Li et al [69] presents a similar performance to that shown by a Bi-LSTM neural network (F1 score of 99%) and a higher performance than unidirectional GRU and LSTM neural networks (F1 score of 93%), as it would be expected.…”

Deep Transfer Learning Model for Semantic Address Matching

“…While Li et al incorporated the hierarchical relationship between address elements into a neural network and proposed a BiLSTM-based multitask learning method [46], Chen et al proposed a contrast learning address matching model based on attention-Bi-LSTM-CNN networks (ABLC) [47]. Subsequently, more and more researchers have used the attention mechanism in their address matching models [48][49][50]. With the popularity of pretrained language models, Lin et al used the classical enhanced sequence inference model (ESIM) [51] for address record pair modelling [21], whereas Xu et al and Qian et al used the BERT model.…”