{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T04:01:46Z","timestamp":1771992106945,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,14]],"date-time":"2021-08-14T00:00:00Z","timestamp":1628899200000},"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":[[2021,8,14]]},"DOI":"10.1145\/3447548.3467392","type":"proceedings-article","created":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T06:13:10Z","timestamp":1628748790000},"page":"1076-1086","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["NewsEmbed: Modeling News through Pre-trained Document Representations"],"prefix":"10.1145","author":[{"given":"Jialu","family":"Liu","sequence":"first","affiliation":[{"name":"Google Research, New York City, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Google Research, New York City, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Yu","sequence":"additional","affiliation":[{"name":"Google Research, New York City, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972764.44"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00288"},{"key":"e_1_3_2_2_3_1","first-page":"137","volume-title":"NeurIPS","author":"Ben-David S.","year":"2007","unstructured":"S. Ben-David , J. Blitzer , K. Crammer , and F. Pereira . Analysis of representations for domain adaptation . In NeurIPS , pages 137 -- 144 , 2007 . S. Ben-David, J. Blitzer, K. Crammer, and F. Pereira. Analysis of representations for domain adaptation. In NeurIPS, pages 137--144, 2007."},{"key":"e_1_3_2_2_4_1","volume-title":"Latent dirichlet allocation. JMLR, 3 (Jan): 993--1022","author":"Blei D. M.","year":"2003","unstructured":"D. M. Blei , A. Y. Ng , and M. I. Jordan . Latent dirichlet allocation. JMLR, 3 (Jan): 993--1022 , 2003 . D. M. Blei, A. Y. Ng, and M. I. Jordan. Latent dirichlet allocation. JMLR, 3 (Jan): 993--1022, 2003."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"e_1_3_2_2_7_1","volume-title":"Language models are few-shot learners. arXiv preprint arXiv:2005.14165","author":"Brown T. B.","year":"2020","unstructured":"T. B. Brown , B. Mann , N. Ryder , M. Subbiah , J. Kaplan , P. Dhariwal , A. Neelakantan , P. Shyam , G. Sastry , A. Askell , Language models are few-shot learners. arXiv preprint arXiv:2005.14165 , 2020 . T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al. Language models are few-shot learners. arXiv preprint arXiv:2005.14165, 2020."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2029"},{"key":"e_1_3_2_2_10_1","volume-title":"ICLR","author":"Chang W.-C.","year":"2020","unstructured":"W.-C. Chang , F. X. Yu , Y.-W. Chang , Y. Yang , and S. Kumar . Pre-training tasks for embedding-based large-scale retrieval . In ICLR , 2020 . W.-C. Chang, F. X. Yu, Y.-W. Chang, Y. Yang, and S. Kumar. Pre-training tasks for embedding-based large-scale retrieval. In ICLR, 2020."},{"key":"e_1_3_2_2_11_1","first-page":"1597","volume-title":"ICML","author":"Chen T.","year":"2020","unstructured":"T. Chen , S. Kornblith , M. Norouzi , and G. Hinton . A simple framework for contrastive learning of visual representations . In ICML , pages 1597 -- 1607 , 2020 . T. Chen, S. Kornblith, M. Norouzi, and G. Hinton. A simple framework for contrastive learning of visual representations. In ICML, pages 1597--1607, 2020."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4330"},{"key":"e_1_3_2_2_13_1","volume-title":"LREC","author":"Conneau A.","year":"2018","unstructured":"A. Conneau and D. Kiela . Senteval: An evaluation toolkit for universal sentence representations . In LREC , 2018 . A. Conneau and D. Kiela. Senteval: An evaluation toolkit for universal sentence representations. In LREC, 2018."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/pra2.2015.145052010082"},{"key":"e_1_3_2_2_16_1","volume-title":"Pre-training with whole word masking for chinese bert. arXiv preprint arXiv:1906.08101","author":"Cui Y.","year":"2019","unstructured":"Y. Cui , W. Che , T. Liu , B. Qin , Z. Yang , S. Wang , and G. Hu . Pre-training with whole word masking for chinese bert. arXiv preprint arXiv:1906.08101 , 2019 . Y. Cui, W. Che, T. Liu, B. Qin, Z. Yang, S. Wang, and G. Hu. Pre-training with whole word masking for chinese bert. arXiv preprint arXiv:1906.08101, 2019."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3270323.3270328"},{"key":"e_1_3_2_2_18_1","volume-title":"NATO Workshop","author":"Deligiannis N.","year":"2018","unstructured":"N. Deligiannis , T. Huu , D. M. Nguyen , and X. Luo . Deep learning for geolocating social media users and detecting fake news . In NATO Workshop , 2018 . N. Deligiannis, T. Huu, D. M. Nguyen, and X. Luo. Deep learning for geolocating social media users and detecting fake news. In NATO Workshop, 2018."},{"key":"e_1_3_2_2_19_1","first-page":"4171","volume-title":"NAACL","author":"Devlin J.","year":"2019","unstructured":"J. Devlin , M.-W. Chang , K. Lee , and K. Toutanova . Bert: Pre-training of deep bidirectional transformers for language understanding . In NAACL , pages 4171 -- 4186 , 2019 . J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL, pages 4171--4186, 2019."},{"key":"e_1_3_2_2_20_1","first-page":"350","volume-title":"Unsupervised construction of large paraphrase corpora: Exploiting massively parallel news sources","author":"Dolan W.","year":"2004","unstructured":"W. Dolan , C. Quirk , C. Brockett , and B. Dolan . Unsupervised construction of large paraphrase corpora: Exploiting massively parallel news sources . pages 350 -- 356 , 2004 . W. Dolan, C. Quirk, C. Brockett, and B. Dolan. Unsupervised construction of large paraphrase corpora: Exploiting massively parallel news sources. pages 350--356, 2004."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1102"},{"key":"e_1_3_2_2_22_1","volume-title":"Cert: Contrastive self-supervised learning for language understanding. arXiv preprint arXiv:2005.12766","author":"Fang H.","year":"2020","unstructured":"H. Fang and P. Xie . Cert: Contrastive self-supervised learning for language understanding. arXiv preprint arXiv:2005.12766 , 2020 . H. Fang and P. Xie. Cert: Contrastive self-supervised learning for language understanding. arXiv preprint arXiv:2005.12766, 2020."},{"key":"e_1_3_2_2_23_1","volume-title":"Language-agnostic bert sentence embedding. arXiv preprint arXiv:2007.01852","author":"Feng F.","year":"2020","unstructured":"F. Feng , Y. Yang , D. Cer , N. Arivazhagan , and W. Wang . Language-agnostic bert sentence embedding. arXiv preprint arXiv:2007.01852 , 2020 . F. Feng, Y. Yang, D. Cer, N. Arivazhagan, and W. Wang. Language-agnostic bert sentence embedding. arXiv preprint arXiv:2007.01852, 2020."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143892"},{"key":"e_1_3_2_2_25_1","volume-title":"Bootstrap your own latent: A new approach to self-supervised learning. arXiv preprint arXiv:2006.07733","author":"Grill J.-B.","year":"2020","unstructured":"J.-B. Grill , F. Strub , F. Altch\u00e9 , C. Tallec , P. H. Richemond , E. Buchatskaya , C. Doersch , B. A. Pires , Z. D. Guo , M. G. Azar , Bootstrap your own latent: A new approach to self-supervised learning. arXiv preprint arXiv:2006.07733 , 2020 . J.-B. Grill, F. Strub, F. Altch\u00e9, C. Tallec, P. H. Richemond, E. Buchatskaya, C. Doersch, B. A. Pires, Z. D. Guo, M. G. Azar, et al. Bootstrap your own latent: A new approach to self-supervised learning. arXiv preprint arXiv:2006.07733, 2020."},{"key":"e_1_3_2_2_26_1","volume-title":"ICML","author":"Guo R.","year":"2020","unstructured":"R. Guo , P. Sun , E. Lindgren , Q. Geng , D. Simcha , F. Chern , and S. Kumar . Accelerating large-scale inference with anisotropic vector quantization . In ICML , 2020 . R. Guo, P. Sun, E. Lindgren, Q. Geng, D. Simcha, F. Chern, and S. Kumar. Accelerating large-scale inference with anisotropic vector quantization. In ICML, 2020."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172131"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_30_1","first-page":"4411","volume-title":"ICML","author":"Hu J.","year":"2020","unstructured":"J. Hu , S. Ruder , A. Siddhant , G. Neubig , O. Firat , and M. Johnson . Xtreme: A massively multilingual multi-task benchmark for evaluating cross-lingual generalisation . In ICML , pages 4411 -- 4421 . PMLR, 2020 . J. Hu, S. Ruder, A. Siddhant, G. Neubig, O. Firat, and M. Johnson. Xtreme: A massively multilingual multi-task benchmark for evaluating cross-lingual generalisation. In ICML, pages 4411--4421. PMLR, 2020."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/645326.649721"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/1610075.1610135"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.3390\/info10040150"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33617-2_34"},{"key":"e_1_3_2_2_35_1","volume-title":"Cross-lingual language model pretraining. arXiv preprint arXiv:1901.07291","author":"Lample G.","year":"2019","unstructured":"G. Lample and A. Conneau . Cross-lingual language model pretraining. arXiv preprint arXiv:1901.07291 , 2019 . G. Lample and A. Conneau. Cross-lingual language model pretraining. arXiv preprint arXiv:1901.07291, 2019."},{"key":"e_1_3_2_2_36_1","volume-title":"Contrastive representation learning: A framework and review","author":"Le-Khac P. H.","year":"2020","unstructured":"P. H. Le-Khac , G. Healy , and A. F. Smeaton . Contrastive representation learning: A framework and review . IEEE Access , 2020 . P. H. Le-Khac, G. Healy, and A. F. Smeaton. Contrastive representation learning: A framework and review. IEEE Access, 2020."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2009937"},{"key":"e_1_3_2_2_38_1","first-page":"216","volume-title":"LREC","author":"Marelli M.","year":"2014","unstructured":"M. Marelli , S. Menini , M. Baroni , L. Bentivogli , R. Bernardi , R. Zamparelli , A sick cure for the evaluation of compositional distributional semantic models . In LREC , pages 216 -- 223 , 2014 . M. Marelli, S. Menini, M. Baroni, L. Bentivogli, R. Bernardi, R. Zamparelli, et al. A sick cure for the evaluation of compositional distributional semantic models. In LREC, pages 216--223, 2014."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1006"},{"key":"e_1_3_2_2_40_1","first-page":"3111","volume-title":"NeurIPS","volume":"26","author":"Mikolov T.","year":"2013","unstructured":"T. Mikolov , I. Sutskever , K. Chen , G. S. Corrado , and J. Dean . Distributed representations of words and phrases and their compositionality . In NeurIPS , volume 26 , pages 3111 -- 3119 , 2013 . T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. Distributed representations of words and phrases and their compositionality. In NeurIPS, volume 26, pages 3111--3119, 2013."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1483"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"e_1_3_2_2_43_1","volume-title":"Machine learning: a probabilistic perspective","author":"Murphy K. P.","year":"2012","unstructured":"K. P. Murphy . Machine learning: a probabilistic perspective . 2012 . K. P. Murphy. Machine learning: a probabilistic perspective. 2012."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098108"},{"key":"e_1_3_2_2_45_1","volume-title":"Y. Li, and O. Vinyals. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"A.","year":"2018","unstructured":"A. v. d. Oord , Y. Li, and O. Vinyals. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 , 2018 . A. v. d. Oord, Y. Li, and O. Vinyals. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748, 2018."},{"key":"e_1_3_2_2_46_1","first-page":"6086","volume-title":"LREC","author":"Oshikawa R.","year":"2020","unstructured":"R. Oshikawa , J. Qian , and W. Y. Wang . A survey on natural language processing for fake news detection . In LREC , pages 6086 -- 6093 , 2020 . R. Oshikawa, J. Qian, and W. Y. Wang. A survey on natural language processing for fake news detection. In LREC, pages 6086--6093, 2020."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"e_1_3_2_2_49_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel C.","year":"2020","unstructured":"C. Raffel , N. Shazeer , A. Roberts , K. Lee , S. Narang , M. Matena , Y. Zhou , W. Li , and P. J. Liu . Exploring the limits of transfer learning with a unified text-to-text transformer . JMLR , 21 : 1 -- 67 , 2020 . C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu. Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR, 21: 1--67, 2020.","journal-title":"JMLR"},{"key":"e_1_3_2_2_50_1","volume-title":"Journal of the American Statistical association, 66 (336): 846--850","author":"Rand W. M.","year":"1971","unstructured":"W. M. Rand . Objective criteria for the evaluation of clustering methods. Journal of the American Statistical association, 66 (336): 846--850 , 1971 . W. M. Rand. Objective criteria for the evaluation of clustering methods. Journal of the American Statistical association, 66 (336): 846--850, 1971."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1317"},{"key":"e_1_3_2_2_52_1","volume-title":"In Proceedings of the LREC 2010 workshop on new challenges for NLP frameworks","author":"Rehurek R.","year":"2010","unstructured":"R. Rehurek and P. Sojka . Software framework for topic modelling with large corpora . In In Proceedings of the LREC 2010 workshop on new challenges for NLP frameworks , 2010 . R. Rehurek and P. Sojka. Software framework for topic modelling with large corpora. In In Proceedings of the LREC 2010 workshop on new challenges for NLP frameworks, 2010."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1089\/big.2020.0062"},{"key":"e_1_3_2_2_55_1","first-page":"5998","volume-title":"NeurIPS","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani , N. Shazeer , N. Parmar , J. Uszkoreit , L. Jones , A. N. Gomez , ?. Kaiser, and I. Polosukhin . Attention is all you need . In NeurIPS , pages 5998 -- 6008 , 2017 . A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, ?. Kaiser, and I. Polosukhin. Attention is all you need. In NeurIPS, pages 5998--6008, 2017."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2000.899541"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330665"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.331"},{"key":"e_1_3_2_2_60_1","volume-title":"mt5: A massively multilingual pre-trained text-to-text transformer. arXiv preprint arXiv:2010.11934","author":"Xue L.","year":"2020","unstructured":"L. Xue , N. Constant , A. Roberts , M. Kale , R. Al-Rfou , A. Siddhant , A. Barua , and C. Raffel . mt5: A massively multilingual pre-trained text-to-text transformer. arXiv preprint arXiv:2010.11934 , 2020 . L. Xue, N. Constant, A. Roberts, M. Kale, R. Al-Rfou, A. Siddhant, A. Barua, and C. Raffel. mt5: A massively multilingual pre-trained text-to-text transformer. arXiv preprint arXiv:2010.11934, 2020."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939673"},{"key":"e_1_3_2_2_62_1","volume-title":"Text understanding from scratch. arXiv preprint arXiv:1502.01710","author":"Zhang X.","year":"2015","unstructured":"X. Zhang and Y. LeCun . Text understanding from scratch. arXiv preprint arXiv:1502.01710 , 2015 . X. Zhang and Y. LeCun. Text understanding from scratch. arXiv preprint arXiv:1502.01710, 2015."},{"key":"e_1_3_2_2_63_1","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume":"28","author":"Zhang X.","year":"2015","unstructured":"X. Zhang , J. Zhao , and Y. LeCun . Character-level convolutional networks for text classification . NeurIPS , 28 : 649 -- 657 , 2015 . X. Zhang, J. Zhao, and Y. LeCun. Character-level convolutional networks for text classification. NeurIPS, 28: 649--657, 2015.","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_64_1","volume-title":"A c-lstm neural network for text classification. arXiv preprint arXiv:1511.08630","author":"Zhou C.","year":"2015","unstructured":"C. Zhou , C. Sun , Z. Liu , and F. Lau . A c-lstm neural network for text classification. arXiv preprint arXiv:1511.08630 , 2015 . C. Zhou, C. Sun, Z. Liu, and F. Lau. A c-lstm neural network for text classification. arXiv preprint arXiv:1511.08630, 2015."}],"event":{"name":"KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Virtual Event Singapore","acronym":"KDD '21","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 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467392","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3447548.3467392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:36Z","timestamp":1750191516000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467392"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,14]]},"references-count":64,"alternative-id":["10.1145\/3447548.3467392","10.1145\/3447548"],"URL":"https:\/\/doi.org\/10.1145\/3447548.3467392","relation":{},"subject":[],"published":{"date-parts":[[2021,8,14]]},"assertion":[{"value":"2021-08-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}