{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T16:06:57Z","timestamp":1769270817307,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539189","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:41Z","timestamp":1660331201000},"page":"4372-4380","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Multilingual Taxonomic Web Page Classification for Contextual Targeting at Yahoo"],"prefix":"10.1145","author":[{"given":"Eric","family":"Ye","sequence":"first","affiliation":[{"name":"Yahoo Research, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Bai","sequence":"additional","affiliation":[{"name":"Yahoo Research, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neil","family":"O'Hare","sequence":"additional","affiliation":[{"name":"Yahoo Research, San Francisco, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eliyar","family":"Asgarieh","sequence":"additional","affiliation":[{"name":"Yahoo Research, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kapil","family":"Thadani","sequence":"additional","affiliation":[{"name":"Yahoo Research, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francisco","family":"Perez-Sorrosal","sequence":"additional","affiliation":[{"name":"Yahoo Research, San Francisco, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sujyothi","family":"Adiga","sequence":"additional","affiliation":[{"name":"Yahoo, Bangalore, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2036264.2036278"},{"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","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-2102-4_59"},{"key":"e_1_3_2_2_4_1","unstructured":"Kush Bhatia Himanshu Jain Purushottam Kar Manik Varma and Prateek Jain. 2015. Sparse local embeddings for extreme multi-label classification. In Advances in Neural Information Processing Systems. 730--738."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277837"},{"key":"e_1_3_2_2_6_1","unstructured":"Tom B. Brown Benjamin Pickman Mann Nick Ryder Melanie Subbiah Jean Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Kr\u00fcger Tom Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric J Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. arXiv:2005.14165. Retrieved from https:\/\/arxiv.org\/abs\/2005.14165."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_2_10_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Conneau Alexis","year":"2019","unstructured":"Alexis Conneau and Guillaume Lample. 2019. Cross-lingual Language Model Pretraining. In Advances in Neural Information Processing Systems, Vol. 32."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1269"},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of NAACL. 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL. 4171--4186."},{"key":"e_1_3_2_2_13_1","volume-title":"Ng","author":"Do Chuong B.","year":"2005","unstructured":"Chuong B. Do and Andrew Y. Ng. 2005. Transfer learning for text classification.. In Advances in Neural Information Processing Systems. 299--306."},{"key":"e_1_3_2_2_14_1","volume-title":"Discriminative Methods for Multi- labeled Classification. Advances in Knowledge Discovery and Data Mining","author":"Godbole Shantanu","year":"2004","unstructured":"Shantanu Godbole and Sunita Sarawagi. 2004. Discriminative Methods for Multi- labeled Classification. Advances in Knowledge Discovery and Data Mining (2004), 22--30."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08373-8"},{"key":"e_1_3_2_2_17_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Hendrycks Dan","year":"2018","unstructured":"Dan Hendrycks, Mantas Mazeika, Duncan Wilson, and Kevin Gimpel. 2018. Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise. In Advances in Neural Information Processing Systems, Vol. 31."},{"key":"e_1_3_2_2_18_1","volume-title":"et al","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, Jeff Dean, et al . 2015. Distilling the knowledge in a neural network. arXiv:1503.02531. Retrieved from https:\/\/arxiv.org\/abs\/1503.02531."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2577361"},{"key":"e_1_3_2_2_21_1","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv:1907.11692. Retrieved from https:\/\/arxiv.org\/abs\/1907.11692."},{"key":"e_1_3_2_2_22_1","volume-title":"Lampert","author":"Phuong Mary","year":"2021","unstructured":"Mary Phuong and Christoph H. Lampert. 2021. Towards Under- standing Knowledge Distillation. arXiv:2105.13093. Retrieved from https:\/\/arxiv.org\/abs\/2105.13093."},{"key":"e_1_3_2_2_23_1","volume-title":"Proceedings of ACL. 4996--5001","author":"Pires Telmo","year":"2019","unstructured":"Telmo Pires, Eva Schlinger, and Dan Garrette. 2019. How Multilingual is Multi- lingual BERT?. In Proceedings of ACL. 4996--5001."},{"key":"e_1_3_2_2_24_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of ICML.","author":"Ren Mengye","year":"2018","unstructured":"Mengye Ren, Wenyuan Zeng, Bin Yang, and Raquel Urtasun. 2018. Learning to Reweight Examples for Robust Deep Learning. In Proceedings of ICML."},{"key":"e_1_3_2_2_26_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2014","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2014. Fitnets: Hints for thin deep nets. arXiv:1412.6550. Retrieved from https:\/\/arxiv.org\/abs\/1412.6550."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11640"},{"key":"e_1_3_2_2_28_1","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2019. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. arXiv:1910.01108. Retrieved from https:\/\/arxiv.org\/abs\/1910.01108."},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of LREC.","author":"Schwenk Holger","year":"2018","unstructured":"Holger Schwenk and Xian Li. 2018. A Corpus for Multilingual Document Classi- fication in Eight Languages. In Proceedings of LREC."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-010-0175-9"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.4018\/jdwm.2007070101"},{"key":"e_1_3_2_2_32_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","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 Advances in Neural Information Processing Systems, Vol. 30."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098135"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.1120.0740"}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","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 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539189","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:59Z","timestamp":1750186979000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539189"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":34,"alternative-id":["10.1145\/3534678.3539189","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539189","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}