{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:54:15Z","timestamp":1781538855536,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,1,30]],"date-time":"2019-01-30T00:00:00Z","timestamp":1548806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Center for Intelligent Information Retrieval"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,1,30]]},"DOI":"10.1145\/3289600.3290978","type":"proceedings-article","created":{"date-parts":[[2019,3,11]],"date-time":"2019-03-11T12:33:01Z","timestamp":1552307581000},"page":"699-707","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Learning to Selectively Transfer"],"prefix":"10.1145","author":[{"given":"Chen","family":"Qu","sequence":"first","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Ji","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghui","family":"Qiu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liu","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyu","family":"Min","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiqing","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"W. Bruce","family":"Croft","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,1,30]]},"reference":[{"key":"e_1_3_2_1_1_1","author":"Arulkumaran K.","year":"2017","unstructured":"K. Arulkumaran , M. P. Deisenroth , M. Brundage , and A. A. Bharath . Deep Reinforcement Learning: A Brief Survey. IEEE Signal Processing Magazine , 2017 . K. Arulkumaran, M. P. Deisenroth, M. Brundage, and A. A. Bharath. Deep Reinforcement Learning: A Brief Survey. IEEE Signal Processing Magazine, 2017.","journal-title":"Deep Reinforcement Learning: A Brief Survey. IEEE Signal Processing Magazine"},{"key":"e_1_3_2_1_2_1","volume-title":"ICLR","author":"Bahdanau D.","year":"2017","unstructured":"D. Bahdanau , P. Brakel , K. Xu , A. Goyal , R. Lowe , J. Pineau , A. C. Courville , and Y. Bengio . An Actor-Critic Algorithm for Sequence Prediction . In ICLR , 2017 . D. Bahdanau, P. Brakel, K. Xu, A. Goyal, R. Lowe, J. Pineau, A. C. Courville, and Y. Bengio. An Actor-Critic Algorithm for Sequence Prediction. In ICLR, 2017."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"e_1_3_2_1_4_1","volume-title":"NIPS","author":"Chen M.","year":"2011","unstructured":"M. Chen , K. Q. Weinberger , and J. C. Blitzer . Co-training for Domain Adaptation . In NIPS , 2011 . M. Chen, K. Q. Weinberger, and J. C. Blitzer. Co-training for Domain Adaptation. In NIPS, 2011."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1152"},{"key":"e_1_3_2_1_6_1","volume-title":"ACL","author":"III.","year":"2007","unstructured":"H.l Daume III. Frustratingly Easy Domain Adaptation . In ACL , 2007 . H.l Daume III. Frustratingly Easy Domain Adaptation. In ACL, 2007."},{"key":"e_1_3_2_1_7_1","volume-title":"CoRR","author":"Fan Y.","year":"2017","unstructured":"Y. Fan , F. Tian , T. Qin , J. Bian , and T. Liu . Learning What Data to Learn . CoRR , 2017 . Y. Fan, F. Tian, T. Qin, J. Bian, and T. Liu. Learning What Data to Learn. CoRR, 2017."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1063"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12063"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983769"},{"key":"e_1_3_2_1_11_1","volume-title":"NIPS","author":"Huang J.","year":"2006","unstructured":"J. Huang , A. J. Smola , A. Gretton , K. M. Borgwardt , and B. Scholkopf . Correcting Sample Selection Bias by Unlabeled Data . In NIPS , 2006 . J. Huang, A. J. Smola, A. Gretton, K. M. Borgwardt, and B. Scholkopf. Correcting Sample Selection Bias by Unlabeled Data. In NIPS, 2006."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12022"},{"key":"e_1_3_2_1_13_1","volume-title":"ICLR","author":"Kingma D. P.","year":"2015","unstructured":"D. P. Kingma and J. L. Ba . Adam: A Method for Stochastic Optimization . In ICLR , 2015 . D. P. Kingma and J. L. Ba. Adam: A Method for Stochastic Optimization. In ICLR, 2015."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133169"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1001"},{"key":"e_1_3_2_1_18_1","volume-title":"CoRR","author":"Mnih V.","year":"2013","unstructured":"V. Mnih , K. Kavukcuoglu , D. Silver , A. Graves , I. Antonoglou , D. Wierstra , and M. A. Riedmiller . Playing Atari with Deep Reinforcement Learning . CoRR , 2013 . V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. A. Riedmiller. Playing Atari with Deep Reinforcement Learning. CoRR, 2013."},{"key":"e_1_3_2_1_19_1","volume-title":"Nature","author":"Mnih V.","year":"2015","unstructured":"V. Mnih , K. Kavukcuoglu , D. Silver , A. A. Rusu , J. Veness , M. G. Bellemare , A. Graves , M. A. Riedmiller , A. Fidjeland , G. Ostrovski , S. Petersen , C. Beattie , A. Sadik , I. Antonoglou , H. King , D. Kumaran , D. Wierstra , S. Legg , and D. Hassabis . Human-level control through deep reinforcement learning . Nature , 2015 . V. Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. A. Riedmiller, A. Fidjeland, G. Ostrovski, S. Petersen, C. Beattie, A. Sadik, I. Antonoglou, H. King, D. Kumaran, D. Wierstra, S. Legg, and D. Hassabis. Human-level control through deep reinforcement learning. Nature, 2015."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1046"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"e_1_3_2_1_23_1","volume-title":"CoRR","author":"Patel Y.","year":"2018","unstructured":"Y. Patel , K. Chitta , and B. Jasani . Learning Sampling Policies for Domain Adaptation . CoRR , 2018 . Y. Patel, K. Chitta, and B. Jasani. Learning Sampling Policies for Domain Adaptation. CoRR, 2018."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/528623"},{"key":"e_1_3_2_1_26_1","volume-title":"NIPS","author":"Socher IR.","year":"2011","unstructured":"011)}Socher2011PoolRAEP IR. Socher and E. H. Huang and J. Pennington and A. Y. Ng and C. D. Manning . Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection . In NIPS , 2011 . 011)}Socher2011PoolRAEPIR. Socher and E. H. Huang and J. Pennington and A. Y. Ng and C. D. Manning. Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection. In NIPS, 2011."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1038"},{"key":"e_1_3_2_1_28_1","volume-title":"On-Line Q-Learning Using Connectionist Systems. Technical report","author":"Rummery G. A.","year":"1994","unstructured":"G. A. Rummery and M. Niranjan . On-Line Q-Learning Using Connectionist Systems. Technical report , University of Cambridge , 1994 . G. A. Rummery and M. Niranjan. On-Line Q-Learning Using Connectionist Systems. Technical report, University of Cambridge, 1994."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11784"},{"key":"e_1_3_2_1_30_1","volume-title":"Nature","author":"Silver D.","year":"2017","unstructured":"D. Silver , J. Schrittwieser , K. Simonyan , I. Antonoglou , A. Huang , A. Guez , T. Hubert , L. R. Baker , M. Lai , A. Bolton , Y. Chen , T. P. Lillicrap , F. Hui , L. Sifre , G. van den Driessche, T. Graepel, and D. Hassabis. Mastering the game of Go without human knowledge . Nature , 2017 . D. Silver, J. Schrittwieser, K. Simonyan, I. Antonoglou, A. Huang, A. Guez, T. Hubert, L. R. Baker, M. Lai, A. Bolton, Y. Chen, T. P. Lillicrap, F. Hui, L. Sifre, G. van den Driessche, T. Graepel, and D. Hassabis. Mastering the game of Go without human knowledge. Nature, 2017."},{"key":"e_1_3_2_1_31_1","volume-title":"Reinforcement Learning - An Introduction . Adaptive Computation and Machine Learning","author":"Sutton R. S.","year":"1998","unstructured":"R. S. Sutton and A. G. Barto . Reinforcement Learning - An Introduction . Adaptive Computation and Machine Learning . MIT Press , 1998 . R. S. Sutton and A. G. Barto. Reinforcement Learning - An Introduction . Adaptive Computation and Machine Learning. MIT Press, 1998."},{"key":"e_1_3_2_1_32_1","volume-title":"AAAI","author":"Wang S.","year":"2018","unstructured":"S. Wang , M. Yu , X. Guo , Z. Wang , T. Klinger , W. Zhang , S. Chang , G. Tesauro , B. Zhou , and J. Jiang . $textR^text3$: Reinforced Ranker-Reader for Open-Domain Question Answering . In AAAI , 2018 . S. Wang, M. Yu, X. Guo, Z. Wang, T. Klinger, W. Zhang, S. Chang, G. Tesauro, B. Zhou, and J. Jiang. $textR^text3$: Reinforced Ranker-Reader for Open-Domain Question Answering. In AAAI, 2018."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"e_1_3_2_1_34_1","volume-title":"Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning. Machine Learning","author":"Williams R. J.","year":"1992","unstructured":"R. J. Williams . Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning. Machine Learning , 1992 . R. J. Williams. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning. Machine Learning, 1992."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1113"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911542"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983818"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210011"},{"key":"e_1_3_2_1_39_1","volume-title":"ICLR","author":"Yang Z.","year":"2017","unstructured":"Z. Yang , R. Salakhutdinov , and W. W. Cohen . Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks . In ICLR , 2017 . Z. Yang, R. Salakhutdinov, and W. W. Cohen. Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks. In ICLR, 2017."},{"key":"e_1_3_2_1_40_1","volume-title":"TACL","author":"Yin NW.","year":"2016","unstructured":"ze, Xiang, and Zhou}Yin2016ABCN NW. Yin , H. Sch\u00fc tze, B. Xiang , and B. Zhou . ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs . TACL , 2016 . ze, Xiang, and Zhou}Yin2016ABCNNW. Yin, H. Sch\u00fc tze, B. Xiang, and B. Zhou. ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs. TACL, 2016."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2086"},{"key":"e_1_3_2_1_42_1","volume-title":"NIPS","author":"Yosinski J.","year":"2014","unstructured":"J. Yosinski , J. Clune , Y. Bengio , and H. Lipson . How Transferable Are Features in Deep Neural Networks ? In NIPS , 2014 . J. Yosinski, J. Clune, Y. Bengio, and H. Lipson. How Transferable Are Features in Deep Neural Networks? In NIPS, 2014."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159685"}],"event":{"name":"WSDM '19: The Twelfth ACM International Conference on Web Search and Data Mining","location":"Melbourne VIC Australia","acronym":"WSDM '19","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3289600.3290978","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3289600.3290978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:21Z","timestamp":1750208541000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3289600.3290978"}},"subtitle":["Reinforced Transfer Learning for Deep Text Matching"],"short-title":[],"issued":{"date-parts":[[2019,1,30]]},"references-count":43,"alternative-id":["10.1145\/3289600.3290978","10.1145\/3289600"],"URL":"https:\/\/doi.org\/10.1145\/3289600.3290978","relation":{},"subject":[],"published":{"date-parts":[[2019,1,30]]},"assertion":[{"value":"2019-01-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}