{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:51:42Z","timestamp":1783439502627,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,5,13]],"date-time":"2019-05-13T00:00:00Z","timestamp":1557705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,5,13]]},"DOI":"10.1145\/3308558.3313456","type":"proceedings-article","created":{"date-parts":[[2019,5,13]],"date-time":"2019-05-13T12:17:59Z","timestamp":1557749879000},"page":"3420-3426","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Place Deduplication with Embeddings"],"prefix":"10.1145","author":[{"given":"Carl","family":"Yang","sequence":"first","affiliation":[{"name":"University of Illinois, Urbana Champaign, 201 N Goodwin Ave, Urbana, IL 61801, USA Facebook Inc., 770 Broadway, New York, NY 10003, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Do Huy","family":"Hoang","sequence":"additional","affiliation":[{"name":"Facebook Inc., 770 Broadway, New York, NY 10003, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomas","family":"Mikolov","sequence":"additional","affiliation":[{"name":"Facebook Inc., 770 Broadway, New York, NY 10003, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Han","sequence":"additional","affiliation":[{"name":"University of Illinois, Urbana Champaign, 201 N Goodwin Ave, Urbana, IL 61801, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,5,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Enriching word vectors with subword information. TACL","author":"Bojanowski Piotr","year":"2017","unstructured":"Piotr Bojanowski , Edouard Grave , Armand Joulin , and Tomas Mikolov . 2017. Enriching word vectors with subword information. TACL ( 2017 ). Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. TACL (2017)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339743"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219928"},{"key":"e_1_3_2_1_4_1","volume-title":"Deep ranking for person re-identification via joint representation learning. TIP25, 5","author":"Chen Shi-Zhe","year":"2016","unstructured":"Shi-Zhe Chen , Chun-Chao Guo , and Jian-Huang Lai . 2016. Deep ranking for person re-identification via joint representation learning. TIP25, 5 ( 2016 ), 2353-2367. Shi-Zhe Chen, Chun-Chao Guo, and Jian-Huang Lai. 2016. Deep ranking for person re-identification via joint representation learning. TIP25, 5 (2016), 2353-2367."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.145"},{"key":"e_1_3_2_1_6_1","first-page":"1335","article-title":"Person re-identification by multi-channel parts-based cnn with improved triplet loss function","author":"Cheng De","year":"2016","unstructured":"De Cheng , Yihong Gong , Sanping Zhou , Jinjun Wang , and Nanning Zheng . 2016 . Person re-identification by multi-channel parts-based cnn with improved triplet loss function . In CVPR. IEEE , 1335 - 1344 . De Cheng, Yihong Gong, Sanping Zhou, Jinjun Wang, and Nanning Zheng. 2016. Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In CVPR. IEEE, 1335-1344.","journal-title":"CVPR. IEEE"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2015.63"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2741715"},{"key":"e_1_3_2_1_9_1","first-page":"1518","article-title":"A practical and effective sampling selection strategy for large scale deduplication","author":"Bianco Guilherme Dal","year":"2016","unstructured":"Guilherme Dal Bianco , Renata Galante , Carlos A Heuser , Marcos Gon\u00e7alves , and Sergio Canuto . 2016 . A practical and effective sampling selection strategy for large scale deduplication . In ICDE. IEEE , 1518 - 1519 . Guilherme Dal Bianco, Renata Galante, Carlos A Heuser, Marcos Gon\u00e7alves, and Sergio Canuto. 2016. A practical and effective sampling selection strategy for large scale deduplication. In ICDE. IEEE, 1518-1519.","journal-title":"ICDE. IEEE"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2566486.2568034"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00312"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.04.005"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505637"},{"key":"e_1_3_2_1_14_1","first-page":"1","article-title":"Fast k nearest neighbor search using GPU","author":"Garcia Vincent","year":"2008","unstructured":"Vincent Garcia , Eric Debreuve , and Michel Barlaud . 2008 . Fast k nearest neighbor search using GPU . In CVPRW. IEEE , 1 - 6 . Vincent Garcia, Eric Debreuve, and Michel Barlaud. 2008. Fast k nearest neighbor search using GPU. In CVPRW. IEEE, 1-6.","journal-title":"CVPRW. IEEE"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983769"},{"key":"e_1_3_2_1_16_1","unstructured":"Xifeng Guo Long Gao Xinwang Liu and Jianping Yin. 2017. Improved Deep Embedded Clustering with Local Structure Preservation. In IJCAI.   Xifeng Guo Long Gao Xinwang Liu and Jianping Yin. 2017. Improved Deep Embedded Clustering with Local Structure Preservation. In IJCAI."},{"key":"e_1_3_2_1_17_1","volume-title":"Data mining: concepts and techniques","author":"Han Jiawei","unstructured":"Jiawei Han , Jian Pei , and Micheline Kamber . 2011. Data mining: concepts and techniques . Elsevier . Jiawei Han, Jian Pei, and Micheline Kamber. 2011. Data mining: concepts and techniques. Elsevier."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2874816"},{"key":"e_1_3_2_1_19_1","first-page":"2042","article-title":"Convolutional neural network architectures for matching natural language sentences","author":"Hu Baotian","year":"2014","unstructured":"Baotian Hu , Zhengdong Lu , Hang Li , and Qingcai Chen . 2014 . Convolutional neural network architectures for matching natural language sentences . In NIPS. 2042 - 2050 . Baotian Hu, Zhengdong Lu, Hang Li, and Qingcai Chen. 2014. Convolutional neural network architectures for matching natural language sentences. In NIPS. 2042-2050.","journal-title":"NIPS."},{"key":"e_1_3_2_1_20_1","unstructured":"Jeff Johnson Matthijs Douze and Herve\u00b4 Je\u00b4gou. 2017. Billion-scale similarity search with GPUs. arXiv preprint arXiv:1702.08734(2017).  Jeff Johnson Matthijs Douze and Herve\u00b4 Je\u00b4gou. 2017. Billion-scale similarity search with GPUs. arXiv preprint arXiv:1702.08734(2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2068"},{"key":"e_1_3_2_1_22_1","volume-title":"Comparison of Different Approaches for Hotels Deduplication","author":"Kozhevnikov Ivan","unstructured":"Ivan Kozhevnikov and Vladimir Gorovoy . 2016. Comparison of Different Approaches for Hotels Deduplication . In KESW. Springer , 230-240. Ivan Kozhevnikov and Vladimir Gorovoy. 2016. Comparison of Different Approaches for Hotels Deduplication. In KESW. Springer, 230-240."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767722"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623638"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2662002"},{"key":"e_1_3_2_1_26_1","volume-title":"Nov","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton . 2008. Visualizing data using t-SNE. JMLR9 , Nov ( 2008 ), 2579-2605. Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. JMLR9, Nov (2008), 2579-2605."},{"key":"e_1_3_2_1_27_1","unstructured":"Tomas Mikolov Edouard Grave Piotr Bojanowski Christian Puhrsch and Armand Joulin. 2018. Advances in pre-training distributed word representations. In LREC.  Tomas Mikolov Edouard Grave Piotr Bojanowski Christian Puhrsch and Armand Joulin. 2018. Advances in pre-training distributed word representations. In LREC."},{"key":"e_1_3_2_1_28_1","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov , Ilya Sutskever , Kai Chen , Greg S Corrado , and Jeff Dean . 2013 . Distributed representations of words and phrases and their compositionality . In NIPS. 3111 - 3119 . Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In NIPS. 3111-3119.","journal-title":"NIPS."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/354756.354805"},{"key":"e_1_3_2_1_30_1","first-page":"2793","article-title":"Text Matching as Image Recognition","author":"Pang Liang","year":"2016","unstructured":"Liang Pang , Yanyan Lan , Jiafeng Guo , Jun Xu , Shengxian Wan , and Xueqi Cheng . 2016 . Text Matching as Image Recognition .. In AAAI. 2793 - 2799 . Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Shengxian Wan, and Xueqi Cheng. 2016. Text Matching as Image Recognition.. In AAAI. 2793-2799.","journal-title":"AAAI."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132949"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/1699648.1699690"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098185"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2745396"},{"key":"e_1_3_2_1_35_1","first-page":"1025","article-title":"Inclusive yet selective: Supervised distributional hypernymy detection","author":"Roller Stephen","year":"2014","unstructured":"Stephen Roller , Katrin Erk , and Gemma Boleda . 2014 . Inclusive yet selective: Supervised distributional hypernymy detection . In COLING. 1025 - 1036 . Stephen Roller, Katrin Erk, and Gemma Boleda. 2014. Inclusive yet selective: Supervised distributional hypernymy detection. In COLING. 1025-1036.","journal-title":"COLING."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.29"},{"key":"e_1_3_2_1_37_1","first-page":"815","article-title":"Facenet: A unified embedding for face recognition and clustering","author":"Schroff Florian","year":"2015","unstructured":"Florian Schroff , Dmitry Kalenichenko , and James Philbin . 2015 . Facenet: A unified embedding for face recognition and clustering . In CVPR. IEEE , 815 - 823 . Florian Schroff, Dmitry Kalenichenko, and James Philbin. 2015. Facenet: A unified embedding for face recognition and clustering. In CVPR. IEEE, 815-823.","journal-title":"CVPR. IEEE"},{"key":"e_1_3_2_1_38_1","first-page":"475","article-title":"Deep attributes driven multi-camera person re-identification","author":"Su Chi","year":"2016","unstructured":"Chi Su , Shiliang Zhang , Junliang Xing , Wen Gao , and Qi Tian . 2016 . Deep attributes driven multi-camera person re-identification . In ECCV. 475 - 491 . Chi Su, Shiliang Zhang, Junliang Xing, Wen Gao, and Qi Tian. 2016. Deep attributes driven multi-camera person re-identification. In ECCV. 475-491.","journal-title":"ECCV."},{"key":"e_1_3_2_1_39_1","first-page":"1194","article-title":"Semi-supervised semantic pattern discovery with guidance from unsupervised pattern clusters","author":"Sun Ang","year":"2010","unstructured":"Ang Sun and Ralph Grishman . 2010 . Semi-supervised semantic pattern discovery with guidance from unsupervised pattern clusters . In COLING. 1194 - 1202 . Ang Sun and Ralph Grishman. 2010. Semi-supervised semantic pattern discovery with guidance from unsupervised pattern clusters. In COLING. 1194-1202.","journal-title":"COLING."},{"key":"e_1_3_2_1_40_1","volume-title":"A Multi-level Attention Model for Text Matching","author":"Sun Qiang","unstructured":"Qiang Sun and Yue Wu. 2018. A Multi-level Attention Model for Text Matching . In ICANN. Springer , 142-153. Qiang Sun and Yue Wu. 2018. A Multi-level Attention Model for Text Matching. In ICANN. Springer, 142-153."},{"key":"e_1_3_2_1_41_1","first-page":"2892","article-title":"Deeply learned face representations are sparse, selective, and robust","author":"Sun Yi","year":"2015","unstructured":"Yi Sun , Xiaogang Wang , and Xiaoou Tang . 2015 . Deeply learned face representations are sparse, selective, and robust . In CVPR. IEEE , 2892 - 2900 . Yi Sun, Xiaogang Wang, and Xiaoou Tang. 2015. Deeply learned face representations are sparse, selective, and robust. In CVPR. IEEE, 2892-2900.","journal-title":"CVPR. IEEE"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Dmitry Ustalov Alexander Panchenko and Chris Biemann. 2017. Watset: automatic induction of synsets from a graph of synonyms. In ACL.  Dmitry Ustalov Alexander Panchenko and Chris Biemann. 2017. Watset: automatic induction of synsets from a graph of synonyms. In ACL.","DOI":"10.18653\/v1\/P17-1145"},{"key":"e_1_3_2_1_44_1","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani Ashish","year":"2017","unstructured":"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 NIPS. 5998 - 6008 . 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 NIPS. 5998-6008.","journal-title":"NIPS."},{"key":"e_1_3_2_1_45_1","first-page":"2835","article-title":"A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations","volume":"16","author":"Wan Shengxian","year":"2016","unstructured":"Shengxian Wan , Yanyan Lan , Jiafeng Guo , Jun Xu , Liang Pang , and Xueqi Cheng . 2016 . A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations .. In AAAI , Vol. 16. 2835 - 2841 . Shengxian Wan, Yanyan Lan, Jiafeng Guo, Jun Xu, Liang Pang, and Xueqi Cheng. 2016. A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations.. In AAAI, Vol. 16. 2835-2841.","journal-title":"AAAI"},{"key":"e_1_3_2_1_46_1","first-page":"1288","article-title":"Joint learning of single-image and cross-image representations for person re-identification","author":"Wang Faqiang","year":"2016","unstructured":"Faqiang Wang , Wangmeng Zuo , Liang Lin , David Zhang , and Lei Zhang . 2016 . Joint learning of single-image and cross-image representations for person re-identification . In CVPR. IEEE , 1288 - 1296 . Faqiang Wang, Wangmeng Zuo, Liang Lin, David Zhang, and Lei Zhang. 2016. Joint learning of single-image and cross-image representations for person re-identification. In CVPR. IEEE, 1288-1296.","journal-title":"CVPR. IEEE"},{"key":"e_1_3_2_1_47_1","first-page":"2249","article-title":"Learning to distinguish hypernyms and co-hyponyms","author":"Weeds Julie","year":"2014","unstructured":"Julie Weeds , Daoud Clarke , Jeremy Reffin , David Weir , and Bill Keller . 2014 . Learning to distinguish hypernyms and co-hyponyms . In COLING. 2249 - 2259 . Julie Weeds, Daoud Clarke, Jeremy Reffin, David Weir, and Bill Keller. 2014. Learning to distinguish hypernyms and co-hyponyms. In COLING. 2249-2259.","journal-title":"COLING."},{"key":"e_1_3_2_1_48_1","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","author":"Xie Junyuan","year":"2016","unstructured":"Junyuan Xie , Ross Girshick , and Ali Farhadi . 2016 . Unsupervised deep embedding for clustering analysis . In ICML. IEEE , 478 - 487 . Junyuan Xie, Ross Girshick, and Ali Farhadi. 2016. Unsupervised deep embedding for clustering analysis. In ICML. IEEE, 478-487.","journal-title":"ICML. IEEE"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080809"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098094"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Carl Yang Chao Zhang Xuewen Chen Jieping Ye and Jiawei Han. 2018. Did You Enjoy the Ride: Understanding Passenger Experience via Heterogeneous Network Embedding. In ICDE.  Carl Yang Chao Zhang Xuewen Chen Jieping Ye and Jiawei Han. 2018. Did You Enjoy the Ride: Understanding Passenger Experience via Heterogeneous Network Embedding. In ICDE.","DOI":"10.1109\/ICDE.2018.00158"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2009962"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806500"}],"event":{"name":"WWW '19: The Web Conference","location":"San Francisco CA USA","acronym":"WWW '19","sponsor":["IW3C2 International World Wide Web Conference Committee"]},"container-title":["The World Wide Web Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3308558.3313456","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3308558.3313456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:17Z","timestamp":1750208537000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3308558.3313456"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,13]]},"references-count":53,"alternative-id":["10.1145\/3308558.3313456","10.1145\/3308558"],"URL":"https:\/\/doi.org\/10.1145\/3308558.3313456","relation":{},"subject":[],"published":{"date-parts":[[2019,5,13]]},"assertion":[{"value":"2019-05-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}