{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:08:34Z","timestamp":1765544914446,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T00:00:00Z","timestamp":1697846400000},"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":[[2023,10,21]]},"DOI":"10.1145\/3583780.3615467","type":"proceedings-article","created":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T07:45:42Z","timestamp":1697874342000},"page":"5002-5009","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["DeepTagger: Knowledge Enhanced Named Entity Recognition for Web-Based Ads Queries"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8014-3150","authenticated-orcid":false,"given":"Simiao","family":"Zuo","sequence":"first","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4187-4439","authenticated-orcid":false,"given":"Pengfei","family":"Tang","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8122-6121","authenticated-orcid":false,"given":"Xinyu","family":"Hu","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4902-4304","authenticated-orcid":false,"given":"Qiang","family":"Lou","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4779-9588","authenticated-orcid":false,"given":"Jian","family":"Jiao","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7921-3673","authenticated-orcid":false,"given":"Denis","family":"Charles","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Aghajanyan Armen","year":"2021","unstructured":"Armen Aghajanyan , Akshat Shrivastava , Anchit Gupta , Naman Goyal , Luke Zettlemoyer , and Sonal Gupta . 2021 . Better Fine-Tuning by Reducing Representational Collapse . In 9th International Conference on Learning Representations, ICLR 2021 , Virtual Event, Austria, May 3--7 , 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=OQ08SN70M1V Armen Aghajanyan, Akshat Shrivastava, Anchit Gupta, Naman Goyal, Luke Zettlemoyer, and Sonal Gupta. 2021. Better Fine-Tuning by Reducing Representational Collapse. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=OQ08SN70M1V"},{"key":"e_1_3_2_1_2_1","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Awasthi Abhijeet","year":"2020","unstructured":"Abhijeet Awasthi , Sabyasachi Ghosh , Rasna Goyal , and Sunita Sarawagi . 2020 . Learning from Rules Generalizing Labeled Exemplars . In 8th International Conference on Learning Representations, ICLR 2020 , Addis Ababa, Ethiopia, April 26--30 , 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=SkeuexBtDr Abhijeet Awasthi, Sabyasachi Ghosh, Rasna Goyal, and Sunita Sarawagi. 2020. Learning from Rules Generalizing Labeled Exemplars. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26--30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=SkeuexBtDr"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 2021 Conference of the North American","author":"Cheng Hao","year":"1865","unstructured":"Hao Cheng , Xiaodong Liu , Lis Pereira , Yaoliang Yu , and Jianfeng Gao . 2021b. Posterior Differential Regularization with f-divergence for Improving Model Robustness . In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics , Online , 1078--1089. https:\/\/doi.org\/10. 1865 3\/v1\/2021.naacl-main.85 10.18653\/v1 Hao Cheng, Xiaodong Liu, Lis Pereira, Yaoliang Yu, and Jianfeng Gao. 2021b. Posterior Differential Regularization with f-divergence for Improving Model Robustness. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, 1078--1089. https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.85"},{"key":"e_1_3_2_1_4_1","volume-title":"Priyanka Goyal","author":"Cheng Xiang","year":"2021","unstructured":"Xiang Cheng , Mitchell Bowden , Bhushan Ramesh Bhange , Priyanka Goyal , Thomas Packer, and Faizan Javed. 2021 a. An End-to-End Solution for Named Entity Recognition in eCommerce Search. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2--9, 2021. AAAI Press , 15098--15106. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/17773 Xiang Cheng, Mitchell Bowden, Bhushan Ramesh Bhange, Priyanka Goyal, Thomas Packer, and Faizan Javed. 2021a. An End-to-End Solution for Named Entity Recognition in eCommerce Search. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2--9, 2021. AAAI Press, 15098--15106. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/17773"},{"key":"e_1_3_2_1_5_1","volume-title":"Can Large Language Models Be an Alternative to Human Evaluations? ArXiv preprint","author":"Chiang Cheng-Han","year":"1937","unstructured":"Cheng-Han Chiang and Hung-yi Lee. 2023. Can Large Language Models Be an Alternative to Human Evaluations? ArXiv preprint , Vol. abs\/ 2305 .0 1937 (2023). https:\/\/arxiv.org\/abs\/2305.01937 Cheng-Han Chiang and Hung-yi Lee. 2023. Can Large Language Models Be an Alternative to Human Evaluations? ArXiv preprint, Vol. abs\/2305.01937 (2023). https:\/\/arxiv.org\/abs\/2305.01937"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","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 the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186. https:\/\/doi.org\/10. 18653\/v1\/N19--1423 10.18653\/v1 Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186. https:\/\/doi.org\/10.18653\/v1\/N19--1423"},{"key":"e_1_3_2_1_7_1","volume-title":"Is GPT-3 a Good Data Annotator? ArXiv preprint","author":"Ding Bosheng","year":"2022","unstructured":"Bosheng Ding , Chengwei Qin , Linlin Liu , Lidong Bing , Shafiq Joty , and Boyang Li. 2022. Is GPT-3 a Good Data Annotator? ArXiv preprint , Vol. abs\/ 2212 .10450 ( 2022 ). https:\/\/arxiv.org\/abs\/2212.10450 Bosheng Ding, Chengwei Qin, Linlin Liu, Lidong Bing, Shafiq Joty, and Boyang Li. 2022. Is GPT-3 a Good Data Annotator? ArXiv preprint, Vol. abs\/2212.10450 (2022). https:\/\/arxiv.org\/abs\/2212.10450"},{"key":"e_1_3_2_1_8_1","volume-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping. ArXiv preprint","author":"Dodge Jesse","year":"2020","unstructured":"Jesse Dodge , Gabriel Ilharco , Roy Schwartz , Ali Farhadi , Hannaneh Hajishirzi , and Noah Smith . 2020. Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping. ArXiv preprint , Vol. abs\/ 2002 .06305 ( 2020 ). https:\/\/arxiv.org\/abs\/2002.06305 Jesse Dodge, Gabriel Ilharco, Roy Schwartz, Ali Farhadi, Hannaneh Hajishirzi, and Noah Smith. 2020. Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping. ArXiv preprint, Vol. abs\/2002.06305 (2020). https:\/\/arxiv.org\/abs\/2002.06305"},{"key":"e_1_3_2_1_9_1","volume-title":"3rd International Conference on Learning Representations, ICLR","author":"Goodfellow Ian J.","year":"2015","unstructured":"Ian J. Goodfellow , Jonathon Shlens , and Christian Szegedy . 2015. Explaining and Harnessing Adversarial Examples . In 3rd International Conference on Learning Representations, ICLR 2015 , San Diego, CA , USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds .). http:\/\/arxiv.org\/abs\/1412.6572 Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6572"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 8342--8360","author":"Gururangan Suchin","year":"1865","unstructured":"Suchin Gururangan , Ana Marasovi\u0107 , Swabha Swayamdipta , Kyle Lo , Iz Beltagy , Doug Downey , and Noah A. Smith . 2020. Don't Stop Pretraining: Adapt Language Models to Domains and Tasks . In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 8342--8360 . https:\/\/doi.org\/10. 1865 3\/v1\/2020.acl-main.740 10.18653\/v1 Suchin Gururangan, Ana Marasovi\u0107, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, and Noah A. Smith. 2020. Don't Stop Pretraining: Adapt Language Models to Domains and Tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 8342--8360. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.740"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Jiang Haoming","year":"1865","unstructured":"Haoming Jiang , Danqing Zhang , Tianyu Cao , Bing Yin , and Tuo Zhao . 2021. Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data . In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) . Association for Computational Linguistics , Online , 1775--1789. https:\/\/doi.org\/10. 1865 3\/v1\/2021.acl-long.140 10.18653\/v1 Haoming Jiang, Danqing Zhang, Tianyu Cao, Bing Yin, and Tuo Zhao. 2021. Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Online, 1775--1789. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.140"},{"key":"e_1_3_2_1_12_1","volume-title":"Workshop on challenges in representation learning, ICML","volume":"3","author":"Dong-Hyun","unstructured":"Dong-Hyun Lee et al. 2013. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks . In Workshop on challenges in representation learning, ICML , Vol. 3 . 896. Dong-Hyun Lee et al. 2013. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, Vol. 3. 896."},{"key":"e_1_3_2_1_13_1","volume-title":"BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision. In KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Liang Chen","year":"2020","unstructured":"Chen Liang , Yue Yu , Haoming Jiang , Siawpeng Er , Ruijia Wang , Tuo Zhao , and Chao Zhang . 2020 . BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision. In KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , Virtual Event, CA, USA, August 23--27 , 2020, Rajesh Gupta, Yan Liu, Jiliang Tang, and B. Aditya Prakash (Eds.). ACM, 1054--1064. https:\/\/dl.acm.org\/doi\/10.1145\/3394486.3403149 Chen Liang, Yue Yu, Haoming Jiang, Siawpeng Er, Ruijia Wang, Tuo Zhao, and Chao Zhang. 2020. BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision. In KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA, August 23--27, 2020, Rajesh Gupta, Yan Liu, Jiliang Tang, and B. Aditya Prakash (Eds.). ACM, 1054--1064. https:\/\/dl.acm.org\/doi\/10.1145\/3394486.3403149"},{"key":"e_1_3_2_1_14_1","volume-title":"R-Drop: Regularized Dropout for Neural Networks. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Liang Xiaobo","year":"2021","unstructured":"Xiaobo Liang , Lijun Wu , Juntao Li , Yue Wang , Qi Meng , Tao Qin , Wei Chen , Min Zhang , and Tie-Yan Liu . 2021 . R-Drop: Regularized Dropout for Neural Networks. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021 , NeurIPS 2021, December 6--14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 10890--10905. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/5a66b9200f29ac3fa0ae244cc2a51b39-Abstract.html Xiaobo Liang, Lijun Wu, Juntao Li, Yue Wang, Qi Meng, Tao Qin, Wei Chen, Min Zhang, and Tie-Yan Liu. 2021. R-Drop: Regularized Dropout for Neural Networks. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6--14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 10890--10905. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/5a66b9200f29ac3fa0ae244cc2a51b39-Abstract.html"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.139"},{"key":"e_1_3_2_1_16_1","first-page":"1","article-title":"b. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu Pengfei","year":"2023","unstructured":"Pengfei Liu , Weizhe Yuan , Jinlan Fu , Zhengbao Jiang , Hiroaki Hayashi , and Graham Neubig . 2023 b. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing . Comput. Surveys , Vol. 55 , 9 (2023), 1 -- 35 . Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023 b. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys, Vol. 55, 9 (2023), 1--35.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_17_1","volume-title":"2023 a. A First Look at LLM-Powered Generative News Recommendation. ArXiv preprint","author":"Liu Qijiong","year":"2023","unstructured":"Qijiong Liu , Nuo Chen , Tetsuya Sakai , and Xiao-Ming Wu . 2023 a. A First Look at LLM-Powered Generative News Recommendation. ArXiv preprint , Vol. abs\/ 2305 .06566 ( 2023 ). https:\/\/arxiv.org\/abs\/2305.06566 Qijiong Liu, Nuo Chen, Tetsuya Sakai, and Xiao-Ming Wu. 2023 a. A First Look at LLM-Powered Generative News Recommendation. ArXiv preprint, Vol. abs\/2305.06566 (2023). https:\/\/arxiv.org\/abs\/2305.06566"},{"key":"e_1_3_2_1_18_1","volume-title":"Adversarial training for large neural language models. ArXiv preprint","author":"Liu Xiaodong","year":"2020","unstructured":"Xiaodong Liu , Hao Cheng , Pengcheng He , Weizhu Chen , Yu Wang , Hoifung Poon , and Jianfeng Gao . 2020. Adversarial training for large neural language models. ArXiv preprint , Vol. abs\/ 2004 .08994 ( 2020 ). https:\/\/arxiv.org\/abs\/2004.08994 Xiaodong Liu, Hao Cheng, Pengcheng He, Weizhu Chen, Yu Wang, Hoifung Poon, and Jianfeng Gao. 2020. Adversarial training for large neural language models. ArXiv preprint, Vol. abs\/2004.08994 (2020). https:\/\/arxiv.org\/abs\/2004.08994"},{"key":"e_1_3_2_1_19_1","volume-title":"6th International Conference on Learning Representations, ICLR","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry , Aleksandar Makelov , Ludwig Schmidt , Dimitris Tsipras , and Adrian Vladu . 2018. Towards Deep Learning Models Resistant to Adversarial Attacks . In 6th International Conference on Learning Representations, ICLR 2018 , Vancouver, BC , Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview .net. https:\/\/openreview.net\/forum?id=rJzIBfZAb Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards Deep Learning Models Resistant to Adversarial Attacks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=rJzIBfZAb"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.724"},{"key":"e_1_3_2_1_21_1","volume-title":"Goodfellow","author":"Miyato Takeru","year":"2017","unstructured":"Takeru Miyato , Andrew M. Dai , and Ian J . Goodfellow . 2017 . Adversarial Training Methods for Semi-Supervised Text Classification. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24--26, 2017, Conference Track Proceedings. OpenReview .net. https:\/\/openreview.net\/forum?id=r1X3g2_xl Takeru Miyato, Andrew M. Dai, and Ian J. Goodfellow. 2017. Adversarial Training Methods for Semi-Supervised Text Classification. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24--26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=r1X3g2_xl"},{"key":"e_1_3_2_1_22_1","volume-title":"Virtual adversarial training: a regularization method for supervised and semi-supervised learning","author":"Miyato Takeru","year":"2018","unstructured":"Takeru Miyato , Shin-ichi Maeda, Masanori Koyama , and Shin Ishii . 2018. Virtual adversarial training: a regularization method for supervised and semi-supervised learning . IEEE transactions on pattern analysis and machine intelligence, Vol. 41 , 8 ( 2018 ), 1979--1993. Takeru Miyato, Shin-ichi Maeda, Masanori Koyama, and Shin Ishii. 2018. Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 8 (2018), 1979--1993."},{"key":"e_1_3_2_1_23_1","volume-title":"Uncertainty-aware self-training for text classification with few labels. ArXiv preprint","author":"Mukherjee Subhabrata","year":"2020","unstructured":"Subhabrata Mukherjee and Ahmed Hassan Awadallah . 2020. Uncertainty-aware self-training for text classification with few labels. ArXiv preprint , Vol. abs\/ 2006 .15315 ( 2020 ). https:\/\/arxiv.org\/abs\/2006.15315 Subhabrata Mukherjee and Ahmed Hassan Awadallah. 2020. Uncertainty-aware self-training for text classification with few labels. ArXiv preprint, Vol. abs\/2006.15315 (2020). https:\/\/arxiv.org\/abs\/2006.15315"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.284"},{"key":"e_1_3_2_1_25_1","volume-title":"GPT-4 technical report. arXiv","author":"AI.","year":"2023","unstructured":"Open AI. 2023. GPT-4 technical report. arXiv ( 2023 ). OpenAI. 2023. GPT-4 technical report. arXiv (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke , Sam Gross , Francisco Massa , Adam Lerer , James Bradbury , Gregory Chanan , Trevor Killeen , Zeming Lin , Natalia Gimelshein , Luca Antiga , Alban Desmaison , Andreas K\u00f6 pf, Edward Yang , Zachary DeVito , Martin Raison , Alykhan Tejani , Sasank Chilamkurthy , Benoit Steiner , Lu Fang , Junjie Bai , and Soumith Chintala . 2019 . PyTorch: An Imperative Style , High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019 , NeurIPS 2019, December 8--14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9 -Buc, Emily B. Fox, and Roman Garnett (Eds.). 8024--8035. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/bdbca288fee7f92f2bfa9f7012727740-Abstract.html Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6 pf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8--14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9 -Buc, Emily B. Fox, and Roman Garnett (Eds.). 8024--8035. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/bdbca288fee7f92f2bfa9f7012727740-Abstract.html"},{"key":"e_1_3_2_1_27_1","volume-title":"Regularizing neural networks by penalizing confident output distributions. ArXiv preprint","author":"Pereyra Gabriel","year":"2017","unstructured":"Gabriel Pereyra , George Tucker , Jan Chorowski , \u0141ukasz Kaiser , and Geoffrey Hinton . 2017. Regularizing neural networks by penalizing confident output distributions. ArXiv preprint , Vol. abs\/ 1701 .06548 ( 2017 ). https:\/\/arxiv.org\/abs\/1701.06548 Gabriel Pereyra, George Tucker, Jan Chorowski, \u0141ukasz Kaiser, and Geoffrey Hinton. 2017. Regularizing neural networks by penalizing confident output distributions. ArXiv preprint, Vol. abs\/1701.06548 (2017). https:\/\/arxiv.org\/abs\/1701.06548"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13--18","volume":"7919","author":"Raghunathan Aditi","year":"2020","unstructured":"Aditi Raghunathan , Sang Michael Xie , Fanny Yang , John C. Duchi , and Percy Liang . 2020 . Understanding and Mitigating the Tradeoff between Robustness and Accuracy . In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13--18 July 2020, Virtual Event (Proceedings of Machine Learning Research , Vol. 119). PMLR, 7909-- 7919 . http:\/\/proceedings.mlr.press\/v119\/raghunathan20a.html Aditi Raghunathan, Sang Michael Xie, Fanny Yang, John C. Duchi, and Percy Liang. 2020. Understanding and Mitigating the Tradeoff between Robustness and Accuracy. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13--18 July 2020, Virtual Event (Proceedings of Machine Learning Research, Vol. 119). PMLR, 7909--7919. http:\/\/proceedings.mlr.press\/v119\/raghunathan20a.html"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157797"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Reimers Nils","year":"1865","unstructured":"Nils Reimers and Iryna Gurevych . 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks . In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) . Association for Computational Linguistics , Hong Kong , China, 3982--3992. https:\/\/doi.org\/10. 1865 3\/v1\/D19--1410 10.18653\/v1 Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 3982--3992. https:\/\/doi.org\/10.18653\/v1\/D19--1410"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Chuck Rosenberg Martial Hebert and Henry Schneiderman. 2005. Semi-supervised self-training of object detection models. (2005).  Chuck Rosenberg Martial Hebert and Henry Schneiderman. 2005. Semi-supervised self-training of object detection models. (2005).","DOI":"10.1109\/ACVMOT.2005.107"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nlp4convai-1.5"},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Shafahi Ali","year":"2019","unstructured":"Ali Shafahi , Mahyar Najibi , Amin Ghiasi , Zheng Xu , John P. Dickerson , Christoph Studer , Larry S. Davis , Gavin Taylor , and Tom Goldstein . 2019 . Adversarial training for free! . In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019 , NeurIPS 2019, December 8--14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9 -Buc, Emily B. Fox, and Roman Garnett (Eds.). 3353--3364. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/7503cfacd12053d309b6bed5c89de212-Abstract.html Ali Shafahi, Mahyar Najibi, Amin Ghiasi, Zheng Xu, John P. Dickerson, Christoph Studer, Larry S. Davis, Gavin Taylor, and Tom Goldstein. 2019. Adversarial training for free!. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8--14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9 -Buc, Emily B. Fox, and Roman Garnett (Eds.). 3353--3364. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/7503cfacd12053d309b6bed5c89de212-Abstract.html"},{"key":"e_1_3_2_1_34_1","volume-title":"2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14--16, 2014, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1312","author":"Szegedy Christian","year":"2014","unstructured":"Christian Szegedy , Wojciech Zaremba , Ilya Sutskever , Joan Bruna , Dumitru Erhan , Ian J. Goodfellow , and Rob Fergus . 2014 . Intriguing properties of neural networks . In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14--16, 2014, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1312 .6199 Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian J. Goodfellow, and Rob Fergus. 2014. Intriguing properties of neural networks. In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14--16, 2014, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1312.6199"},{"key":"e_1_3_2_1_35_1","volume-title":"COLING-02: The 6th Conference on Natural Language Learning 2002 (CoNLL-2002)","author":"Erik","year":"2024","unstructured":"Erik F. Tjong Kim Sang. 2002. Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition . In COLING-02: The 6th Conference on Natural Language Learning 2002 (CoNLL-2002) . https:\/\/aclanthology.org\/W02-- 2024 Erik F. Tjong Kim Sang. 2002. Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition. In COLING-02: The 6th Conference on Natural Language Learning 2002 (CoNLL-2002). https:\/\/aclanthology.org\/W02--2024"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/3291264.3291268"},{"key":"e_1_3_2_1_37_1","volume-title":"Is chatgpt a good nlg evaluator? a preliminary study. ArXiv preprint","author":"Wang Jiaan","year":"2023","unstructured":"Jiaan Wang , Yunlong Liang , Fandong Meng , Haoxiang Shi , Zhixu Li , Jinan Xu , Jianfeng Qu , and Jie Zhou . 2023. Is chatgpt a good nlg evaluator? a preliminary study. ArXiv preprint , Vol. abs\/ 2303 .04048 ( 2023 ). https:\/\/arxiv.org\/abs\/2303.04048 Jiaan Wang, Yunlong Liang, Fandong Meng, Haoxiang Shi, Zhixu Li, Jinan Xu, Jianfeng Qu, and Jie Zhou. 2023. Is chatgpt a good nlg evaluator? a preliminary study. ArXiv preprint, Vol. abs\/2303.04048 (2023). https:\/\/arxiv.org\/abs\/2303.04048"},{"key":"e_1_3_2_1_38_1","volume-title":"Chi, Quoc Le, and Denny Zhou","author":"Wei Jason","year":"2022","unstructured":"Jason Wei , Xuezhi Wang , Dale Schuurmans , Maarten Bosma , Ed Chi, Quoc Le, and Denny Zhou . 2022 . Chain of thought prompting elicits reasoning in large language models. ArXiv preprint, Vol. abs\/ 2201 .11903 (2022). https:\/\/arxiv.org\/abs\/2201.11903 Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Quoc Le, and Denny Zhou. 2022. Chain of thought prompting elicits reasoning in large language models. ArXiv preprint, Vol. abs\/2201.11903 (2022). https:\/\/arxiv.org\/abs\/2201.11903"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3365109.3368765"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_41_1","volume-title":"Large language models are diverse role-players for summarization evaluation. ArXiv preprint","author":"Wu Ning","year":"2023","unstructured":"Ning Wu , Ming Gong , Linjun Shou , Shining Liang , and Daxin Jiang . 2023. Large language models are diverse role-players for summarization evaluation. ArXiv preprint , Vol. abs\/ 2303 .15078 ( 2023 ). https:\/\/arxiv.org\/abs\/2303.15078 Ning Wu, Ming Gong, Linjun Shou, Shining Liang, and Daxin Jiang. 2023. Large language models are diverse role-players for summarization evaluation. ArXiv preprint, Vol. abs\/2303.15078 (2023). https:\/\/arxiv.org\/abs\/2303.15078"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19--24, 2016 (JMLR Workshop and Conference Proceedings","volume":"487","author":"Xie Junyuan","year":"2016","unstructured":"Junyuan Xie , Ross B. Girshick , and Ali Farhadi . 2016 . Unsupervised Deep Embedding for Clustering Analysis . In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19--24, 2016 (JMLR Workshop and Conference Proceedings , Vol. 48), Maria-Florina Balcan and Kilian Q. Weinberger (Eds.). JMLR.org, 478-- 487 . http:\/\/proceedings.mlr.press\/v48\/xieb16.html Junyuan Xie, Ross B. Girshick, and Ali Farhadi. 2016. Unsupervised Deep Embedding for Clustering Analysis. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19--24, 2016 (JMLR Workshop and Conference Proceedings, Vol. 48), Maria-Florina Balcan and Kilian Q. Weinberger (Eds.). JMLR.org, 478--487. http:\/\/proceedings.mlr.press\/v48\/xieb16.html"},{"key":"e_1_3_2_1_43_1","volume-title":"Unsupervised Data Augmentation for Consistency Training. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Xie Qizhe","year":"2020","unstructured":"Qizhe Xie , Zihang Dai , Eduard H. Hovy , Thang Luong , and Quoc Le . 2020 . Unsupervised Data Augmentation for Consistency Training. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 , NeurIPS 2020, December 6--12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/44feb0096faa8326192570788b38c1d1-Abstract.html Qizhe Xie, Zihang Dai, Eduard H. Hovy, Thang Luong, and Quoc Le. 2020. Unsupervised Data Augmentation for Consistency Training. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6--12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/44feb0096faa8326192570788b38c1d1-Abstract.html"},{"key":"e_1_3_2_1_44_1","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Xie Sang Michael","year":"2022","unstructured":"Sang Michael Xie , Aditi Raghunathan , Percy Liang , and Tengyu Ma . 2022 . An Explanation of In-context Learning as Implicit Bayesian Inference . In The Tenth International Conference on Learning Representations, ICLR 2022 , Virtual Event, April 25--29 , 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=RdJVFCHjUMI Sang Michael Xie, Aditi Raghunathan, Percy Liang, and Tengyu Ma. 2022. An Explanation of In-context Learning as Implicit Bayesian Inference. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=RdJVFCHjUMI"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.192"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the 2021 Conference of the North American","author":"Yu Yue","year":"1865","unstructured":"Yue Yu , Simiao Zuo , Haoming Jiang , Wendi Ren , Tuo Zhao , and Chao Zhang . 2021. Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach . In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics , Online , 1063--1077. https:\/\/doi.org\/10. 1865 3\/v1\/2021.naacl-main.84 10.18653\/v1 Yue Yu, Simiao Zuo, Haoming Jiang, Wendi Ren, Tuo Zhao, and Chao Zhang. 2021. Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, 1063--1077. https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.84"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481946"},{"key":"e_1_3_2_1_48_1","volume-title":"FreeLB: Enhanced Adversarial Training for Natural Language Understanding. In 8th International Conference on Learning Representations, ICLR 2020","author":"Zhu Chen","year":"2020","unstructured":"Chen Zhu , Yu Cheng , Zhe Gan , Siqi Sun , Tom Goldstein , and Jingjing Liu . 2020 . FreeLB: Enhanced Adversarial Training for Natural Language Understanding. In 8th International Conference on Learning Representations, ICLR 2020 , Addis Ababa, Ethiopia, April 26--30 , 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=BygzbyHFvB Chen Zhu, Yu Cheng, Zhe Gan, Siqi Sun, Tom Goldstein, and Jingjing Liu. 2020. FreeLB: Enhanced Adversarial Training for Natural Language Understanding. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26--30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=BygzbyHFvB"},{"key":"e_1_3_2_1_49_1","first-page":"348","volume-title":"ARCH: Efficient Adversarial Regularized Training with Caching. In Findings of the Association for Computational Linguistics: EMNLP 2021","author":"Zuo Simiao","year":"2021","unstructured":"Simiao Zuo , Chen Liang , Haoming Jiang , Pengcheng He , Xiaodong Liu , Jianfeng Gao , Weizhu Chen , and Tuo Zhao . 2021 a. ARCH: Efficient Adversarial Regularized Training with Caching. In Findings of the Association for Computational Linguistics: EMNLP 2021 . Association for Computational Linguistics, Punta Cana, Dominican Republic, 4118--4131. https:\/\/doi.org\/10. 18653\/v1\/2021.findings-emnlp. 348 10.18653\/v1 Simiao Zuo, Chen Liang, Haoming Jiang, Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen, and Tuo Zhao. 2021a. ARCH: Efficient Adversarial Regularized Training with Caching. In Findings of the Association for Computational Linguistics: EMNLP 2021. Association for Computational Linguistics, Punta Cana, Dominican Republic, 4118--4131. https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.348"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.527"},{"key":"e_1_3_2_1_51_1","volume-title":"Self-Training with Differentiable Teacher. In Findings of the Association for Computational Linguistics: NAACL 2022","author":"Zuo Simiao","year":"2022","unstructured":"Simiao Zuo , Yue Yu , Chen Liang , Haoming Jiang , Siawpeng Er , Chao Zhang , Tuo Zhao , and Hongyuan Zha . 2022 . Self-Training with Differentiable Teacher. In Findings of the Association for Computational Linguistics: NAACL 2022 . Association for Computational Linguistics, Seattle, United States, 933--949. https:\/\/doi.org\/10. 18653\/v1\/2022.findings-naacl.70 10.18653\/v1 Simiao Zuo, Yue Yu, Chen Liang, Haoming Jiang, Siawpeng Er, Chao Zhang, Tuo Zhao, and Hongyuan Zha. 2022. Self-Training with Differentiable Teacher. In Findings of the Association for Computational Linguistics: NAACL 2022. Association for Computational Linguistics, Seattle, United States, 933--949. https:\/\/doi.org\/10.18653\/v1\/2022.findings-naacl.70"}],"event":{"name":"CIKM '23: The 32nd ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Birmingham United Kingdom","acronym":"CIKM '23"},"container-title":["Proceedings of the 32nd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3615467","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583780.3615467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:54Z","timestamp":1750178214000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3615467"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,21]]},"references-count":51,"alternative-id":["10.1145\/3583780.3615467","10.1145\/3583780"],"URL":"https:\/\/doi.org\/10.1145\/3583780.3615467","relation":{},"subject":[],"published":{"date-parts":[[2023,10,21]]},"assertion":[{"value":"2023-10-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}