{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T02:18:14Z","timestamp":1788315494997,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T00:00:00Z","timestamp":1564012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,7,25]]},"DOI":"10.1145\/3292500.3330944","type":"proceedings-article","created":{"date-parts":[[2019,7,26]],"date-time":"2019-07-26T13:17:26Z","timestamp":1564147046000},"page":"1317-1327","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Quantifying Long Range Dependence in Language and User Behavior to improve RNNs"],"prefix":"10.1145","author":[{"given":"Francois","family":"Belletti","sequence":"first","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minmin","family":"Chen","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ed H.","family":"Chi","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,7,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Machine Learning. 1120--1128","author":"Arjovsky Martin","year":"2016"},{"key":"e_1_3_2_1_2_1","volume-title":"Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473","author":"Bahdanau Dzmitry","year":"2014"},{"key":"e_1_3_2_1_3_1","volume-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271","author":"Bai Shaojie","year":"2018"},{"key":"e_1_3_2_1_4_1","volume-title":"Factorized Recurrent Neural Architectures for Longer Range Dependence. In International Conference on Artificial Intelligence and Statistics. 1522--1530","author":"Belletti Francois","year":"2018"},{"key":"e_1_3_2_1_5_1","unstructured":"Francois Belletti Evan Sparks Alexandre Bayen and Joseph Gonzalez. 2017. Random projection design for scalable implicit smoothing of randomly observed stochastic processes. In Artificial Intelligence and Statistics. 700--708.  Francois Belletti Evan Sparks Alexandre Bayen and Joseph Gonzalez. 2017. Random projection design for scalable implicit smoothing of randomly observed stochastic processes. In Artificial Intelligence and Statistics. 700--708."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","volume-title":"Statistics for long-memory processes","author":"Beran Jan","DOI":"10.1201\/9780203738481"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","volume-title":"Time series: data analysis and theory","author":"Brillinger David R","DOI":"10.1137\/1.9780898719246"},{"key":"e_1_3_2_1_8_1","unstructured":"Shiyu Chang Yang Zhang Wei Han Mo Yu Xiaoxiao Guo Wei Tan Xiaodong Cui Michael Witbrock Mark A Hasegawa-Johnson and Thomas S Huang. 2017. Dilated recurrent neural networks. In Advances in Neural Information Processing Systems. 77--87.   Shiyu Chang Yang Zhang Wei Han Mo Yu Xiaoxiao Guo Wei Tan Xiaodong Cui Michael Witbrock Mark A Hasegawa-Johnson and Thomas S Huang. 2017. Dilated recurrent neural networks. In Advances in Neural Information Processing Systems. 77--87."},{"key":"e_1_3_2_1_9_1","volume-title":"One billion word benchmark for measuring progress in statistical language modeling. arXiv preprint arXiv:1312.3005","author":"Chelba Ciprian","year":"2013"},{"key":"e_1_3_2_1_10_1","volume-title":"Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks. arXiv preprint arXiv:1806.05394","author":"Chen Minmin","year":"2018"},{"key":"e_1_3_2_1_11_1","volume-title":"Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014"},{"key":"e_1_3_2_1_12_1","volume-title":"Hierarchical multiscale recurrent neural networks. arXiv preprint arXiv:1609.01704","author":"Chung Junyoung","year":"2016"},{"key":"e_1_3_2_1_13_1","volume-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555","author":"Chung Junyoung","year":"2014"},{"key":"e_1_3_2_1_14_1","volume-title":"Elements of information theory","author":"Cover Thomas M"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079628.3079670"},{"key":"e_1_3_2_1_17_1","volume-title":"Theory and applications of long-range dependence","author":"Doukhan Paul"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","volume-title":"Speech recognition with deep recurrent neural networks","author":"Graves Alex","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459266"},{"key":"e_1_3_2_1_20_1","volume-title":"Information Theory, 2005. ISIT 2005. Proceedings. International Symposium on. IEEE, 719--723","author":"Guo Dongning","year":"2005"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.844072"},{"key":"e_1_3_2_1_22_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_24_1","volume-title":"John Peurifoy, Scott Skirlo, Yann LeCun, Max Tegmark, and Marin Soljavc i\u0107.","author":"Jing Li","year":"2016"},{"key":"e_1_3_2_1_25_1","volume-title":"Exploring the limits of language modeling. arXiv preprint arXiv:1602.02410","author":"Jozefowicz Rafal","year":"2016"},{"key":"e_1_3_2_1_26_1","volume-title":"Criticality in formal languages and statistical physics. arXiv preprint arXiv:1606.06737","author":"Lin Henry W","year":"2016"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2003.1167344"},{"key":"e_1_3_2_1_28_1","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_29_1","volume-title":"Information theory, inference and learning algorithms","author":"MacKay David JC"},{"key":"e_1_3_2_1_30_1","volume-title":"Nature","volume":"391","author":"Mandelbrot Benoit B","year":"1998"},{"key":"e_1_3_2_1_31_1","volume-title":"Nitish Shirish Keskar, and Richard Socher","author":"Merity Stephen","year":"2017"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"e_1_3_2_1_33_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013a. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119.   Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013a. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 746--751","author":"Mikolov Tomas","year":"2013"},{"key":"e_1_3_2_1_35_1","volume-title":"When Recurrent Models Don't Need To Be Recurrent. arXiv preprint arXiv:1805.10369","author":"Miller John","year":"2018"},{"key":"e_1_3_2_1_36_1","volume-title":"International Conference on Machine Learning. 1310--1318","author":"Pascanu Razvan","year":"2013"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","volume-title":"Long-range dependence and self-similarity","author":"Pipiras Vladas","DOI":"10.1017\/CBO9781139600347"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109896"},{"key":"e_1_3_2_1_40_1","unstructured":"Ali Rahimi and Benjamin Recht. 2008. Random features for large-scale kernel machines. In Advances in neural information processing systems. 1177--1184.   Ali Rahimi and Benjamin Recht. 2008. Random features for large-scale kernel machines. In Advances in neural information processing systems. 1177--1184."},{"key":"e_1_3_2_1_41_1","volume-title":"Log-periodogram regression of time series with long range dependence. The annals of Statistics","author":"Robinson Peter M","year":"1995"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1561\/0900000004"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372071"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3125486.3125488"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04174-1"},{"key":"e_1_3_2_1_46_1","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. 3104--3112.   Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. 3104--3112."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313650"},{"key":"e_1_3_2_1_48_1","volume-title":"Learning longer-term dependencies in rnns with auxiliary losses. arXiv preprint arXiv:1803.00144","author":"Trinh Trieu H","year":"2018"},{"key":"e_1_3_2_1_49_1","unstructured":"A\"aron Van Den Oord Sander Dieleman Heiga Zen Karen Simonyan Oriol Vinyals Alex Graves Nal Kalchbrenner Andrew W Senior and Koray Kavukcuoglu. 2016. WaveNet: A generative model for raw audio.. In SSW. 125.  A\"aron Van Den Oord Sander Dieleman Heiga Zen Karen Simonyan Oriol Vinyals Alex Graves Nal Kalchbrenner Andrew W Senior and Koray Kavukcuoglu. 2016. WaveNet: A generative model for raw audio.. In SSW. 125."},{"key":"e_1_3_2_1_50_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.   Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_1_51_1","volume-title":"On orthogonality and learning recurrent networks with long term dependencies. arXiv preprint arXiv:1702.00071","author":"Vorontsov Eugene","year":"2017"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018689"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109911"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.173"},{"key":"e_1_3_2_1_55_1","volume-title":"Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122","author":"Yu Fisher","year":"2015"}],"event":{"name":"KDD '19: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Anchorage AK USA","acronym":"KDD '19","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3292500.3330944","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3292500.3330944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:26:04Z","timestamp":1750206364000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3292500.3330944"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,25]]},"references-count":55,"alternative-id":["10.1145\/3292500.3330944","10.1145\/3292500"],"URL":"https:\/\/doi.org\/10.1145\/3292500.3330944","relation":{},"subject":[],"published":{"date-parts":[[2019,7,25]]},"assertion":[{"value":"2019-07-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}