{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T03:52:14Z","timestamp":1784865134000,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"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":[[2022,7,6]]},"DOI":"10.1145\/3477495.3531971","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:13Z","timestamp":1657206733000},"page":"1455-1465","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Entity-aware Transformers for Entity Search"],"prefix":"10.1145","author":[{"given":"Emma J.","family":"Gerritse","sequence":"first","affiliation":[{"name":"Radboud University, Nijmegen, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Faegheh","family":"Hasibi","sequence":"additional","affiliation":[{"name":"Radboud University, Nijmegen, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arjen P.","family":"de Vries","sequence":"additional","affiliation":[{"name":"Radboud University, Nijmegen, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proc. of 27th International Conference on Computational Linguistics (COLING '18)","author":"Akbik Alan","year":"2018","unstructured":"Alan Akbik , Duncan Blythe , and Roland Vollgraf . 2018 . Contextual String Embeddings for Sequence Labeling . In Proc. of 27th International Conference on Computational Linguistics (COLING '18) . 1638--1649. Alan Akbik, Duncan Blythe, and Roland Vollgraf. 2018. Contextual String Embeddings for Sequence Labeling. In Proc. of 27th International Conference on Computational Linguistics (COLING '18). 1638--1649."},{"key":"e_1_3_2_1_2_1","series-title":"The Information Retrieval Series","volume-title":"Entity-Oriented Search","author":"Balog Krisztian","unstructured":"Krisztian Balog . 2018. Entity-Oriented Search . The Information Retrieval Series , Vol. 39 . Springer . Krisztian Balog. 2018. Entity-Oriented Search. The Information Retrieval Series, Vol. 39. Springer."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2685317"},{"key":"e_1_3_2_1_4_1","volume-title":"Proc. of the 26th International Conference on Neural Information Processing Systems (NeurIPS '13)","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes , Nicolas Usunier , Alberto Garcia-Duran , Jason Weston , and Oksana Yakhnenko . 2013 . Translating embeddings for modeling multi-relational data . In Proc. of the 26th International Conference on Neural Information Processing Systems (NeurIPS '13) . 2787--2795. Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Proc. of the 26th International Conference on Neural Information Processing Systems (NeurIPS '13). 2787--2795."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1063"},{"key":"e_1_3_2_1_6_1","volume-title":"Proc. of the International Conference on Learning Representations (ICLR '21)","author":"Cao Nicola De","year":"2021","unstructured":"Nicola De Cao , Gautier Izacard , Sebastian Riedel , and Fabio Petroni . 2021 . Autoregressive Entity Retrieval . In Proc. of the International Conference on Learning Representations (ICLR '21) . Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. 2021. Autoregressive Entity Retrieval. In Proc. of the International Conference on Learning Representations (ICLR '21)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883061"},{"key":"e_1_3_2_1_8_1","volume-title":"TREC CAsT 2019: The conversational assistance track overview. arXiv preprint","author":"Dalton Jeffrey","year":"2020","unstructured":"Jeffrey Dalton , Chenyan , and Jamie Callan . 2020. TREC CAsT 2019: The conversational assistance track overview. arXiv preprint ( 2020 ). arXiv:2003.13624 Jeffrey Dalton, Chenyan , and Jamie Callan. 2020. TREC CAsT 2019: The conversational assistance track overview. arXiv preprint (2020). arXiv:2003.13624"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609628"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450141"},{"key":"e_1_3_2_1_11_1","volume-title":"Proc. of The North American Chapter of the Association for Computational Linguistics '19 (NAACL '19)","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 Proc. of The North American Chapter of the Association for Computational Linguistics '19 (NAACL '19) . 4171--4186. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proc. of The North American Chapter of the Association for Computational Linguistics '19 (NAACL '19). 4171--4186."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331257"},{"key":"e_1_3_2_1_13_1","volume-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping. arXiv preprint arXiv:2002.06305","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 arXiv:2002.06305 ( 2020 ). 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 arXiv:2002.06305 (2020)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1871437.1871689"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-018-9346-x"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45439-5_7"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2808194.2809473"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2970398.2970406"},{"key":"e_1_3_2_1_19_1","volume-title":"Effectiveness. In Proc. of the 39th European Conference on Information Retrieval (ECIR '17)","author":"Hasibi Faegheh","year":"2017","unstructured":"Faegheh Hasibi , Krisztian Balog , and Svein Erik Bratsberg . 2017 . Entity Linking in Queries: Efficiency vs . Effectiveness. In Proc. of the 39th European Conference on Information Retrieval (ECIR '17) . 40--53. Faegheh Hasibi, Krisztian Balog, and Svein Erik Bratsberg. 2017. Entity Linking in Queries: Efficiency vs. Effectiveness. In Proc. of the 39th European Conference on Information Retrieval (ECIR '17). 40--53."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3084149"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080751"},{"key":"e_1_3_2_1_22_1","volume-title":"Improving Efficient Neural Ranking Models with CrossArchitecture Knowledge Distillation. arXiv preprint","author":"Hofst\u00e4tter Sebastian","year":"2020","unstructured":"Sebastian Hofst\u00e4tter , Sophia Althammer , Michael Schr\u00f6der , Mete Sertkan , and Allan Hanbury . 2020. Improving Efficient Neural Ranking Models with CrossArchitecture Knowledge Distillation. arXiv preprint ( 2020 ). arXiv:2010.02666 Sebastian Hofst\u00e4tter, Sophia Althammer, Michael Schr\u00f6der, Mete Sertkan, and Allan Hanbury. 2020. Improving Efficient Neural Ranking Models with CrossArchitecture Knowledge Distillation. arXiv preprint (2020). arXiv:2010.02666"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.479"},{"key":"e_1_3_2_1_24_1","volume-title":"Radboud University at TREC CAsT","author":"Joko Hideaki","year":"2021","unstructured":"Hideaki Joko , Emma J Gerritse , Faegheh Hasibi , and Arjen P de Vries . 2022. Radboud University at TREC CAsT 2021 . In TREC. Hideaki Joko, Emma J Gerritse, Faegheh Hasibi, and Arjen P de Vries. 2022. Radboud University at TREC CAsT 2021. In TREC."},{"key":"e_1_3_2_1_25_1","volume-title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans. Transactions of the Association for Computational Linguistics","author":"Joshi Mandar","year":"2020","unstructured":"Mandar Joshi , Danqi Chen , Yinhan Liu , Daniel S. Weld , Luke Zettlemoyer , and Omer Levy . 2020. SpanBERT: Improving Pre-training by Representing and Predicting Spans. Transactions of the Association for Computational Linguistics ( 2020 ), 64--77. Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2020. SpanBERT: Improving Pre-training by Representing and Predicting Spans. Transactions of the Association for Computational Linguistics (2020), 64--77."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1588"},{"key":"e_1_3_2_1_27_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint","author":"Liu Yinhan","year":"2019","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 preprint ( 2019 ). arXiv:1907.11692 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 preprint (2019). arXiv:1907.11692"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"e_1_3_2_1_29_1","volume-title":"Proc. of Advances in Neural Information Processing Systems (NeurIPS '13)","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov , Ilya Sutskever , Kai Chen , Gregory S. Corrado , and Jeffrey Dean . 2013 . Distributed Representations of Words and Phrases and their Compositionality . In Proc. of Advances in Neural Information Processing Systems (NeurIPS '13) . 3111--3119. Tomas Mikolov, Ilya Sutskever, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. In Proc. of Advances in Neural Information Processing Systems (NeurIPS '13). 3111--3119."},{"key":"e_1_3_2_1_30_1","volume-title":"Proc. of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen , Mir Rosenberg , Xia Song , Jianfeng Gao , Saurabh Tiwary , Rangan Majumder , and Li Deng . 2016 . MS MARCO: A Human Generated MAchine Reading COmprehension Dataset . In Proc. of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches 2016. Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In Proc. of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches 2016."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45439-5_10"},{"key":"e_1_3_2_1_32_1","volume-title":"Passage Re-ranking with BERT. arXiv preprint","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira and Kyunghyun Cho . 2019. Passage Re-ranking with BERT. arXiv preprint ( 2019 ). arXiv:1901.04085 Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. arXiv preprint (2019). arXiv:1901.04085"},{"key":"e_1_3_2_1_33_1","volume-title":"Multi-stage document ranking with BERT. arXiv preprint","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira , Wei Yang , Kyunghyun Cho , and Jimmy Lin . 2019. Multi-stage document ranking with BERT. arXiv preprint ( 2019 ). arXiv:1910.14424 Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, and Jimmy Lin. 2019. Multi-stage document ranking with BERT. arXiv preprint (2019). arXiv:1910.14424"},{"key":"e_1_3_2_1_34_1","volume-title":"Proc. of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP '19)","author":"Peters Matthew E.","unstructured":"Matthew E. Peters , Mark Neumann , Robert Logan , Roy Schwartz , Vidur Joshi , Sameer Singh , and Noah A. Smith . 2019. Knowledge Enhanced Contextual Word Representations . In Proc. of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP '19) . 43--54. Matthew E. Peters, Mark Neumann, Robert Logan, Roy Schwartz, Vidur Joshi, Sameer Singh, and Noah A. Smith. 2019. Knowledge Enhanced Contextual Word Representations. In Proc. of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP '19). 43--54."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"e_1_3_2_1_36_1","volume-title":"Bowman","author":"Phang Jason","year":"2019","unstructured":"Jason Phang , Thibault Fevry , and Samuel R . Bowman . 2019 . Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks . arXiv preprint arXiv:1811.01088 (2019). Jason Phang, Thibault Fevry, and Samuel R. Bowman. 2019. Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks. arXiv preprint arXiv:1811.01088 (2019)."},{"key":"e_1_3_2_1_37_1","volume-title":"E-BERT: EfficientYet-Effective Entity Embeddings for BERT. In Findings of the Association for Computational Linguistics (ELMNLP '20)","author":"Poerner Nina","year":"2020","unstructured":"Nina Poerner , Ulli Waltinger , and Hinrich Sch\u00fctze . 2020 . E-BERT: EfficientYet-Effective Entity Embeddings for BERT. In Findings of the Association for Computational Linguistics (ELMNLP '20) . 803--818. Nina Poerner, Ulli Waltinger, and Hinrich Sch\u00fctze. 2020. E-BERT: EfficientYet-Effective Entity Embeddings for BERT. In Findings of the Association for Computational Linguistics (ELMNLP '20). 803--818."},{"key":"e_1_3_2_1_38_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel , Noam Shazeer , Adam Roberts , Katherine Lee , Sharan Narang , Michael Matena , Yanqi Zhou , Wei Li , and Peter J. Liu . 2020 . Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer . Journal of Machine Learning Research 21 , 140 (2020), 1 -- 67 . Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research 21, 140 (2020), 1--67.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00342"},{"key":"e_1_3_2_1_40_1","volume-title":"Proc. of 35th Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (NeurIPS '21)","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur , Nils Reimers , Andreas R\u00fcckl\u00e9 , Abhishek Srivastava , and Iryna Gurevych . 2021 . BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models . In Proc. of 35th Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (NeurIPS '21) . Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Proc. of 35th Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (NeurIPS '21)."},{"key":"e_1_3_2_1_41_1","volume-title":"Proc. of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '20)","author":"van Hulst Johannes M.","unstructured":"Johannes M. van Hulst , Faegheh Hasibi , Koen Dercksen , Krisztian Balog , and Arjen P . de Vries. 2020. REL: An Entity Linker Standing on the Shoulders of Giants . In Proc. of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '20) . Johannes M. van Hulst, Faegheh Hasibi, Koen Dercksen, Krisztian Balog, and Arjen P. de Vries. 2020. REL: An Entity Linker Standing on the Shoulders of Giants. In Proc. of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '20)."},{"key":"e_1_3_2_1_42_1","volume-title":"Language Models are Open Knowledge Graphs. arXiv preprint","author":"Wang Chenguang","year":"2020","unstructured":"Chenguang Wang , Xiao Liu , and Dawn Song . 2020. Language Models are Open Knowledge Graphs. arXiv preprint ( 2020 ). arXiv:2010.11967 Chenguang Wang, Xiao Liu, and Dawn Song. 2020. Language Models are Open Knowledge Graphs. arXiv preprint (2020). arXiv:2010.11967"},{"key":"e_1_3_2_1_43_1","volume-title":"Guihong Cao, Daxin Jiang, and Ming Zhou.","author":"Wang Ruize","year":"2020","unstructured":"Ruize Wang , Duyu Tang , Nan Duan , Zhongyu Wei , Xuanjing Huang , Jianshu ji , Guihong Cao, Daxin Jiang, and Ming Zhou. 2020 . K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters . arXiv preprint (2020). arXiv:2002.01808 Ruize Wang, Duyu Tang, Nan Duan, Zhongyu Wei, Xuanjing Huang, Jianshu ji, Guihong Cao, Daxin Jiang, and Ming Zhou. 2020. K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters. arXiv preprint (2020). arXiv:2002.01808"},{"key":"e_1_3_2_1_44_1","volume-title":"Proc. of Advances in Neural Information Processing Systems (NeurIPS '21)","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang , Furu Wei , Li Dong , Hangbo Bao , Nan Yang , and Ming Zhou . 2020 . MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers . In Proc. of Advances in Neural Information Processing Systems (NeurIPS '21) , H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Eds.). 5776--5788. Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers. In Proc. of Advances in Neural Information Processing Systems (NeurIPS '21), H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Eds.). 5776--5788."},{"key":"e_1_3_2_1_45_1","volume-title":"KEPLER: A unified model for knowledge embedding and pre-trained language representation. arXiv preprint","author":"Wang Xiaozhi","year":"2019","unstructured":"Xiaozhi Wang , Tianyu Gao , Zhaocheng Zhu , Zhiyuan Liu , Juanzi Li , and Jian Tang . 2019 . KEPLER: A unified model for knowledge embedding and pre-trained language representation. arXiv preprint (2019). arXiv:1911.06136 Xiaozhi Wang, Tianyu Gao, Zhaocheng Zhu, Zhiyuan Liu, Juanzi Li, and Jian Tang. 2019. KEPLER: A unified model for knowledge embedding and pre-trained language representation. arXiv preprint (2019). arXiv:1911.06136"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1599"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080768"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052558"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.4"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.523"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1025"},{"key":"e_1_3_2_1_52_1","volume-title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding. In Advances in Neural Information Processing Systems (NeurIPS '19)","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang , Zihang Dai , Yiming Yang , Jaime Carbonell , Russ R Salakhutdinov , and Quoc V Le . 2019 . XLNet: Generalized Autoregressive Pretraining for Language Understanding. In Advances in Neural Information Processing Systems (NeurIPS '19) . 5753--5763. Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. XLNet: Generalized Autoregressive Pretraining for Language Understanding. In Advances in Neural Information Processing Systems (NeurIPS '19). 5753--5763."},{"key":"e_1_3_2_1_53_1","volume-title":"Proc. of 2021 International Conference on Learning Representations (ICLR '20)","author":"Zhang Tianyi","year":"2021","unstructured":"Tianyi Zhang , Felix Wu , Arzoo Katiyar , Kilian Q Weinberger , and Yoav Artzi . 2021 . Revisiting Few-sample BERT Fine-tuning . In Proc. of 2021 International Conference on Learning Representations (ICLR '20) . Tianyi Zhang, Felix Wu, Arzoo Katiyar, Kilian Q Weinberger, and Yoav Artzi. 2021. Revisiting Few-sample BERT Fine-tuning. In Proc. of 2021 International Conference on Learning Representations (ICLR '20)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Madrid Spain","acronym":"SIGIR '22","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531971","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3531971","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:20Z","timestamp":1750183820000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531971"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":54,"alternative-id":["10.1145\/3477495.3531971","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3531971","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]},"assertion":[{"value":"2022-07-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}