Abstract
Geo-textual objects with both geographical location and textual description are gaining in prevalence. Over the past decades, substantial research has been conducted on spatial keyword queries, which integrate location into keyword-based querying of geo-textual content. However, existing proposals mostly focus on efficiency for processing spatial keyword queries, and little effort was made to address the effectiveness perspectives.
In this work, using two datasets with ground truth query results, we evaluate the effectiveness of standard spatial keyword queries. Our evaluation results show that the TkQ query that ranks objects by a weighted combination of spatial proximity and text relevance is the most effective. Motivated by the finding, we propose a Deep relevance with Weight learning (DrW) model to further improve the effectiveness of the retrieval ranking. DrW is featured with two novel ideas: First, we propose a neural network architecture to learn the text relevance matching over the local interaction between the query and geo-textual objects. Second, we find that a query-dependent weight to balance text relevance and spatial proximity in ranking can improve effectiveness, and we develop a learning-based method to learn the query-dependent weight. Experimental results reveal that our model outperforms state-of-the-art methods on effectiveness, with improvements up to 32.15%, 32.34%, and 33.00% in terms of NDCG@3, NDCG@5, and MRR.
Supplemental Material
- Ritesh Ahuja, Nikos Armenatzoglou, Dimitris Papadias, and George J Fakas. 2015. Geo-social keyword search. In SSTD. Springer, 431--450.Google Scholar
- Xin Cao, Gao Cong, and Christian S. Jensen. 2010. Retrieving Top-k Prestige-Based Relevant Spatial Web Objects. In VLDB. 373--384.Google Scholar
- Xin Cao, Gao Cong, Christian S Jensen, and Beng Chin Ooi. 2011. Collective spatial keyword querying. In SIGMOD. 373--384.Google Scholar
- Zhe Cao, Tao Qin, Tie-Yan Liu, Ming-Feng Tsai, and Hang Li. 2007. Learning to rank: from pairwise approach to listwise approach. In ICML. 129--136.Google Scholar
- Ariel Cary, Ouri Wolfson, and Naphtali Rishe. 2010. Efficient and Scalable Method for Processing Top-k Spatial Boolean Queries. In SSDBM. 87--95.Google Scholar
- Gang Chen, Jingwen Zhao, Yunjun Gao, Lei Chen, and Rui Chen. 2017. Time-Aware Boolean Spatial Keyword Queries. IEEE Trans. Knowl. Data Eng., Vol. 29, 11 (2017), 2601--2614.Google ScholarDigital Library
- Lisi Chen, Gao Cong, Christian S. Jensen, and Dingming Wu. 2013. Spatial Keyword Query Processing: An Experimental Evaluation. In VLDB. 217--228.Google Scholar
- Yile Chen, Xiucheng Li, Gao Cong, Cheng Long, Zhifeng Bao, Shang Liu, Wanli Gu, and Fuzheng Zhang. 2021b. Points-of-interest relationship inference with spatial-enriched graph neural networks. In VLDB. 504--512.Google Scholar
- Yen-Yu Chen, Torsten Suel, and Alexander Markowetz. 2006. Efficient query processing in geographic web search engines. In SIGMOD. 277--288.Google Scholar
- Zhida Chen, Lisi Chen, Gao Cong, and Christian S. Jensen. 2021a. Location- and keyword-based querying of geo-textual data: a survey. In VLDB. 603--640.Google Scholar
- Maria Christoforaki, Jinru He, Constantinos Dimopoulos, Alexander Markowetz, and Torsten Suel. 2011. Text vs. space: efficient geo-search query processing. In CIKM. 423--432.Google Scholar
- Gao Cong, Christian S. Jensen, and Dingming Wu. 2009. Efficient Retrieval of the Top-k Most Relevant Spatial Web Objects. In VLDB. 337--348.Google Scholar
- Ian De Felipe, Vagelis Hristidis, and Naphtali Rishe. 2008. Keyword Search on Spatial Databases. In ICDE. 656--665.Google Scholar
- Jianfeng Gao, Patrick Pantel, Michael Gamon, Xiaodong He, and Li Deng. 2014. Modeling Interestingness with Deep Neural Networks. In EMNLP. 2--13.Google Scholar
- Richard Gö bel, Andreas Henrich, Raik Niemann, and Daniel Blank. 2009. A hybrid index structure for geo-textual searches. In CIKM. 1625--1628.Google Scholar
- Jiafeng Guo, Yixing Fan, Qingyao Ai, and W. Bruce Croft. 2016. A Deep Relevance Matching Model for Ad-hoc Retrieval. In CIKM. 55--64.Google Scholar
- Ramaswamy Hariharan, Bijit Hore, Chen Li, and Sharad Mehrotra. 2007. Processing Spatial-Keyword (SK) Queries in Geographic Information Retrieval (GIR) Systems. In SSDBM. 16.Google Scholar
- Baotian Hu, Zhengdong Lu, Hang Li, and Qingcai Chen. 2014. Convolutional Neural Network Architectures for Matching Natural Language Sentences. In NeurIPS. 2042--2050.Google Scholar
- Jizhou Huang, Haifeng Wang, Yibo Sun, Miao Fan, Zhengjie Huang, Chunyuan Yuan, and Yawen Li. 2021. HGAMN: Heterogeneous Graph Attention Matching Network for Multilingual POI Retrieval at Baidu Maps. In SIGKDD. 3032--3040.Google Scholar
- Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, and Larry P. Heck. 2013. Learning deep structured semantic models for web search using click through data. In CIKM. 2333--2338.Google ScholarDigital Library
- Weihuang Huang, Guoliang Li, Kian-Lee Tan, and Jianhua Feng. 2012. Efficient safe-region construction for moving top-K spatial keyword queries. In CIKM. 932--941.Google Scholar
- Jinling Jiang, Hua Lu, Bin Yang, and Bin Cui. 2015. Finding top-k local users in geo-tagged social media data. In ICDE. 267--278.Google Scholar
- Ali Khodaei, Cyrus Shahabi, and Chen Li. 2012. SKIF-P: a point-based indexing and ranking of web documents for spatial-keyword search. Geoinformatica, Vol. 16, 3 (2012), 563--596.Google ScholarDigital Library
- Zhisheng Li, Ken CK Lee, Baihua Zheng, Wang-Chien Lee, Dik Lee, and Xufa Wang. 2010. Ir-tree: An efficient index for geographic document search. TKDE, Vol. 23, 4 (2010), 585--599.Google Scholar
- Cheng Long, Raymond Chi-Wing Wong, Ke Wang, and Ada Wai-Chee Fu. 2013. Collective spatial keyword queries: a distance owner-driven approach. In SIGMOD. 689--700.Google Scholar
- Jiaheng Lu, Ying Lu, and Gao Cong. 2011. Reverse spatial and textual k nearest neighbor search. In SIGMOD. 349--360.Google Scholar
- Ahmed R. Mahmood and Walid G. Aref. 2019. Scalable Processing of Spatial-Keyword Queries.Google Scholar
- Paras Mehta, Dimitrios Skoutas, and Agnès Voisard. 2015. Spatio-temporal keyword queries for moving objects. In SIGSPATIAL. 1--4.Google Scholar
- Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Shengxian Wan, and Xueqi Cheng. 2016. Text Matching as Image Recognition. In AAAI. 2793--2799.Google Scholar
- Jay M. Ponte and W. Bruce Croft. 2017. A Language Modeling Approach to Information Retrieval. In SIGIR. 202--208.Google Scholar
- Zhihu Qian, Jiajie Xu, Kai Zheng, Pengpeng Zhao, and Xiaofang Zhou. 2018. Semantic-aware top-k spatial keyword queries. World Wide Web, Vol. 21, 3 (2018), 573--594.Google ScholarDigital Library
- Stephen E. Robertson and Steve Walker. 1994. Some Simple Effective Approximations to the 2-Poisson Model for Probabilistic Weighted Retrieval. In SIGIR. 232--241.Google ScholarDigital Library
- Jo a o B. Rocha-Junior, Orestis Gkorgkas, Simon Jonassen, and Kjetil Nørvåg. 2011. Efficient Processing of Top-k Spatial Keyword Queries. In SSTD. 205--222.Google Scholar
- Yelong Shen, Xiaodong He, Jianfeng Gao, Li Deng, and Gré goire Mesnil. 2014. Learning semantic representations using convolutional neural networks for web search. In WWW. 373--374.Google Scholar
- Yufei Tao and Cheng Sheng. 2013. Fast nearest neighbor search with keywords. TKDE, Vol. 26, 4 (2013), 878--888.Google Scholar
- Subodh Vaid, Christopher B Jones, Hideo Joho, and Mark Sanderson. 2005. Spatio-textual indexing for geographical search on the web. In SSTD. 218--235.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS. 5998--6008.Google Scholar
- Dingming Wu, Man Lung Yiu, Christian S. Jensen, and Gao Cong. 2011. Efficient continuously moving top-k spatial keyword query processing. In ICDE. 541--552.Google Scholar
- Xike Xie, Xin Lin, Jianliang Xu, and Christian S. Jensen. 2017. Reverse Keyword-Based Location Search. In ICDE. 375--386.Google Scholar
- Zixuan Yuan, Hao Liu, Yanchi Liu, Denghui Zhang, Fei Yi, Nengjun Zhu, and Hui Xiong. 2020. Spatio-Temporal Dual Graph Attention Network for Query-POI Matching. In SIGIR. 629--638.Google Scholar
- Matthew D. Zeiler. 2012. ADADELTA: An Adaptive Learning Rate Method. CoRR, Vol. abs/1212.5701 (2012).Google Scholar
- Chengyuan Zhang, Ying Zhang, Wenjie Zhang, and Xuemin Lin. 2013b. Inverted linear quadtree: Efficient top k spatial keyword search. In ICDE. 901--912.Google Scholar
- Dongxiang Zhang, Yeow Meng Chee, Anirban Mondal, Anthony K. H. Tung, and Masaru Kitsuregawa. 2009. Keyword Search in Spatial Databases: Towards Searching by Document. In ICDE. 688--699.Google Scholar
- Dongxiang Zhang, Beng Chin Ooi, and Anthony K. H. Tung. 2010. Locating mapped resources in Web 2.0. In ICDE. 521--532.Google Scholar
- Dongxiang Zhang, Kian-Lee Tan, and Anthony KH Tung. 2013a. Scalable top-k spatial keyword search. In EDBT. 359--370.Google Scholar
- Ji Zhao, Dan Peng, Chuhan Wu, Huan Chen, Meiyu Yu, Wanji Zheng, Li Ma, Hua Chai, Jieping Ye, and Xiaohu Qie. 2019. Incorporating Semantic Similarity with Geographic Correlation for Query-POI Relevance Learning. In AAAI. 1270--1277.Google Scholar
- Yinghua Zhou, Xing Xie, Chuang Wang, Yuchang Gong, and Wei-Ying Ma. 2005. Hybrid index structures for location-based web search. In CIKM. 155--162.Google Scholar
Index Terms
- Effectiveness Perspectives and a Deep Relevance Model for Spatial Keyword Queries
Recommendations
Preference-based top-k spatial keyword queries
MLBS '11: Proceedings of the 1st international workshop on Mobile location-based serviceWith proliferation of geo-positioning and geo-tagging, spatial keyword query has been an attractive and challenging topic that blooms various interesting applications in spatial databases. However, spatial keyword queries in those fields do not always ...
Less Data Delivers Higher Search Effectiveness for Keyword Queries
SSDBM '19: Proceedings of the 31st International Conference on Scientific and Statistical Database ManagementAs many users, such as scientists, do not know the schema and/or content of their databases, they cannot precisely formulate their information needs using formal query languages, such as SQL. To help these users, researchers have proposed keyword query ...
Top-k coupled keyword recommendation for relational keyword queries
Providing top-k typical relevant keyword queries would benefit the users who cannot formulate appropriate queries to express their imprecise query intentions. By extracting the semantic relationships both between keywords and keyword queries, this paper ...
Comments