{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T11:42:32Z","timestamp":1791459752429,"version":"4.3.4"},"reference-count":101,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:00:00Z","timestamp":1716940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Australian Research Council (ARC) Discovery Projects","award":["DP200102940"],"award-info":[{"award-number":["DP200102940"]}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"crossref","award":["DP220103044"],"award-info":[{"award-number":["DP220103044"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2024,5,29]]},"abstract":"<jats:p>Large-scale software-intensive systems often produce a large volume of logs to record runtime status and events for troubleshooting purposes. The rich information in log data enables a variety of system management and diagnosis tasks. Over the years, many approaches have been proposed for automated log analytics. However, these approaches usually design separate models for each specific task, which cannot be generalized to other tasks. They are also not robust when dealing with logs from heterogeneous sources. In this paper, we propose PreLog, a novel pre-trained model for log analytics. PreLog is pre-trained on a large amount of unlabelled log data to capture the semantic meaning of logs. We design two log-specific pre-training objectives, including entry-level and sequence-level objectives, which enable PreLog to better understand the hidden structure and semantics of logs. To perform downstream log analytics tasks, we leverage a prompt tuning paradigm to convert downstream tasks' objectives into a similar form as the pre-training stage. We have conducted extensive experiments on two main log analytics tasks (i.e., log parsing and log-based anomaly detection). Experimental results show that PreLog achieves better or comparable results in comparison with the state-of-the-art, task-specific approaches. PreLog is cost-effective and can be uniformly applied to many log analytics tasks through the prompt tuning paradigm.<\/jats:p>","DOI":"10.1145\/3654966","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T09:44:53Z","timestamp":1717062293000},"page":"1-28","source":"Crossref","is-referenced-by-count":33,"title":["PreLog: A Pre-trained Model for Log Analytics"],"prefix":"10.1145","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7651-9154","authenticated-orcid":false,"given":"Van-Hoang","family":"Le","sequence":"first","affiliation":[{"name":"The University of Newcastle &amp; Chongqing University, Newcastle, New South Wales, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3063-9425","authenticated-orcid":false,"given":"Hongyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,30]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Retrieved","year":"2023","unstructured":"2023. Application and Infrastructure Monitoring -- Amazon CloudWatch. Retrieved Oct 10, 2023 from https: \/\/aws.amazon.com\/cloudwatch\/"},{"key":"e_1_2_1_2_1","volume-title":"Retrieved","year":"2023","unstructured":"2023. Centralized Logging on AWS. Retrieved Oct 10, 2023 from https:\/\/aws.amazon.com\/solutions\/implementations\/ centralized-logging\/"},{"key":"e_1_2_1_3_1","volume-title":"Beats & Logstash. Retrieved","author":"Stack Elastic","year":"2023","unstructured":"2023. Elastic Stack: Elasticsearch, Kibana, Beats & Logstash. Retrieved Oct 10, 2023 from https:\/\/www.elastic.co\/elasticstack\/"},{"key":"e_1_2_1_4_1","volume-title":"Retrieved","year":"2023","unstructured":"2023. Implementation of PLELog. Retrieved August 27, 2023 from https:\/\/github.com\/YangLin-George\/PLELog"},{"key":"e_1_2_1_5_1","volume-title":"Retrieved","year":"2023","unstructured":"2023. Logz.io: Cloud Observability and Security, Powered by Open Source. Retrieved Oct 10, 2023 from https:\/\/logz.io"},{"key":"e_1_2_1_6_1","unstructured":"2023. OpenAI ChatGPT. Retrieved Oct 6 2023 from https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_2_1_7_1","volume-title":"PreLog repository. Retrieved","year":"2023","unstructured":"2023. PreLog repository. Retrieved Oct 6, 2023 from https:\/\/github.com\/LogIntelligence\/PreLog"},{"key":"e_1_2_1_8_1","volume-title":"Retrieved","year":"2023","unstructured":"2023. Splunk: The Key to Enterprise Resilience. Retrieved Oct 10, 2023 from http:\/\/www.splunk.com"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of the 6th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","volume":"4","author":"Barham Paul","year":"2004","unstructured":"Paul Barham, Austin Donnelly, Rebecca Isaacs, and Richard Mortier. 2004. Using Magpie for request extraction and workload modelling.. In Proceedings of the 6th USENIX Symposium on Operating Systems Design and Implementation (OSDI), Vol. 4. 18--18."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid54584.2022.00044"},{"key":"e_1_2_1_12_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00542"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2004.1301345"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626719"},{"key":"e_1_2_1_16_1","volume-title":"LogAI: A Library for Log Analytics and Intelligence. arXiv preprint arXiv:2301.13415","author":"Cheng Qian","year":"2023","unstructured":"Qian Cheng, Amrita Saha, Wenzhuo Yang, Chenghao Liu, Doyen Sahoo, and Steven Hoi. 2023. LogAI: A Library for Log Analytics and Intelligence. arXiv preprint arXiv:2301.13415 (2023)."},{"key":"e_1_2_1_17_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Yunxuan Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"e_1_2_1_19_1","volume-title":"Weiyi Shang, and Tse-Hsun Chen.","author":"Dai Hetong","year":"2020","unstructured":"Hetong Dai, Heng Li, Che Shao Chen, Weiyi Shang, and Tse-Hsun Chen. 2020. Logram: Efficient log parsing using n-gram dictionaries. IEEE Transactions on Software Engineering (2020)."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00012"},{"key":"e_1_2_1_21_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). 4171--4186."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.10"},{"key":"e_1_2_1_23_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0103"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134015"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.deelio-1.4"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_2_1_28_1","volume-title":"Execution anomaly detection in distributed systems through unstructured log analysis. In 2009 ninth IEEE international conference on data mining","author":"Fu Qiang","unstructured":"Qiang Fu, Jian-Guang Lou, Yi Wang, and Jiang Li. 2009. Execution anomaly detection in distributed systems through unstructured log analysis. In 2009 ninth IEEE international conference on data mining. IEEE, 149--158."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589292"},{"key":"e_1_2_1_32_1","volume-title":"GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations.","author":"Guo Daya","year":"2021","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie LIU, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao Kun Deng, Colin Clement, Dawn Drain, Neel Sundaresan, Jian Yin, Daxin Jiang, and Ming Zhou. 2021. GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations."},{"key":"e_1_2_1_33_1","volume-title":"Translog: A unified transformer-based framework for log anomaly detection. arXiv preprint arXiv:2201.00016","author":"Guo Hongcheng","year":"2021","unstructured":"Hongcheng Guo, Xingyu Lin, Jian Yang, Yi Zhuang, Jiaqi Bai, Tieqiao Zheng, Bo Zhang, and Zhoujun Li. 2021. Translog: A unified transformer-based framework for log anomaly detection. arXiv preprint arXiv:2201.00016 (2021)."},{"key":"e_1_2_1_34_1","volume-title":"Logbert: Log anomaly detection via bert. In 2021 international joint conference on neural networks (IJCNN)","author":"Guo Haixuan","year":"2021","unstructured":"Haixuan Guo, Shuhan Yuan, and Xintao Wu. 2021. Logbert: Log anomaly detection via bert. In 2021 international joint conference on neural networks (IJCNN). IEEE, 1--8."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS.2017.13"},{"key":"e_1_2_1_37_1","volume-title":"A survey on automated log analysis for reliability engineering. ACM computing surveys (CSUR) 54, 6","author":"He Shilin","year":"2021","unstructured":"Shilin He, Pinjia He, Zhuangbin Chen, Tianyi Yang, Yuxin Su, and Michael R Lyu. 2021. A survey on automated log analysis for reliability engineering. ACM computing surveys (CSUR) 54, 6 (2021), 1--37."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2016.21"},{"key":"e_1_2_1_39_1","volume-title":"Loghub: a large collection of system log datasets towards automated log analytics. arXiv preprint arXiv:2008.06448","author":"He Shilin","year":"2020","unstructured":"Shilin He, Jieming Zhu, Pinjia He, and Michael R Lyu. 2020. Loghub: a large collection of system log datasets towards automated log analytics. arXiv preprint arXiv:2008.06448 (2020)."},{"key":"e_1_2_1_40_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.3034647"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3257518"},{"key":"e_1_2_1_43_1","volume-title":"34th IEEE International Symposium on Software Reliability Engineering, ISSRE. IEEE, 391--402","author":"Huo Yintong","unstructured":"Yintong Huo, Cheryl Lee, Yuxin Su, Shiwen Shan, Jinyang Liu, and Michael R. Lyu. 2023. EvLog: Identifying Anomalous Logs over Software Evolution. In 34th IEEE International Symposium on Software Reliability Engineering, ISSRE. IEEE, 391--402."},{"key":"e_1_2_1_44_1","volume-title":"SemParser: A Semantic Parser for Log Analytics. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 881--893","author":"Huo Yintong","year":"2023","unstructured":"Yintong Huo, Yuxin Su, Cheryl Lee, and Michael R Lyu. 2023. SemParser: A Semantic Parser for Log Analytics. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 881--893."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588918"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2017.64"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-017-9518-0"},{"key":"e_1_2_1_48_1","volume-title":"Anomaly detection on OpenStack logs based on an improved robust principal component analysis model and its projection onto column space","author":"Kalaki Parisa Sadat","year":"2022","unstructured":"Parisa Sadat Kalaki, Alireza Shameli-Sendi, and Behzad Khalaji Emamzadeh Abbasi. 2022. Anomaly detection on OpenStack logs based on an improved robust principal component analysis model and its projection onto column space. Software: Practice and Experience (2022)."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510101"},{"key":"e_1_2_1_50_1","volume-title":"International Conference on Learning Representations.","author":"Kim Jaehyung","year":"2021","unstructured":"Jaehyung Kim, Dongyeop Kang, Sungsoo Ahn, and Jinwoo Shin. 2021. What makes better augmentation strategies? augment difficult but not too different. In International Conference on Learning Representations."},{"key":"e_1_2_1_51_1","volume-title":"Log-based Anomaly Detection Without Log Parsing. In 2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE). 492--504","author":"Le Van-Hoang","year":"2021","unstructured":"Van-Hoang Le and Hongyu Zhang. 2021. Log-based Anomaly Detection Without Log Parsing. In 2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE). 492--504."},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510155"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00206"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00204"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00150"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367516"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE5003.2020.00018"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2889160.2889232"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00085"},{"key":"e_1_2_1_61_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","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 arXiv:1907.11692 (2019)."},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511993"},{"key":"e_1_2_1_63_1","volume-title":"Detecting anomaly in big data system logs using convolutional neural network. In 2018 DASC\/PiCom\/DataCom\/CyberSciTech","author":"Lu Siyang","unstructured":"Siyang Lu, Xiang Wei, Yandong Li, and Liqiang Wang. 2018. Detecting anomaly in big data system logs using convolutional neural network. In 2018 DASC\/PiCom\/DataCom\/CyberSciTech. IEEE, 151--158."},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.420"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.232078"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3511561"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/658"},{"key":"e_1_2_1_68_1","first-page":"23102","article-title":"Coco-lm: Correcting and contrasting text sequences for language model pretraining","volume":"34","author":"Meng Yu","year":"2021","unstructured":"Yu Meng, Chenyan Xiong, Payal Bajaj, Paul Bennett, Jiawei Han, Xia Song, et al. 2021. Coco-lm: Correcting and contrasting text sequences for language model pretraining. Advances in Neural Information Processing Systems 34 (2021), 23102--23114.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196321.3196340"},{"key":"e_1_2_1_70_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC","author":"Grave \u00c9douard","year":"2018","unstructured":"Tom\u00e1? Mikolov, \u00c9douard Grave, Piotr Bojanowski, Christian Puhrsch, and Armand Joulin. 2018. Advances in Pre-Training Distributed Word Representations. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)."},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363217"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2010.5463281"},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00148"},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67667-4_8"},{"key":"e_1_2_1_75_1","volume-title":"37th annual IEEE\/IFIP international conference on dependable systems and networks (DSN'07)","author":"Oliner Adam","unstructured":"Adam Oliner and Jon Stearley. 2007. What supercomputers say: A study of five system logs. In 37th annual IEEE\/IFIP international conference on dependable systems and networks (DSN'07). IEEE, 575--584."},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2015.14"},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"e_1_2_1_78_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_2_1_79_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_2_1_81_1","volume-title":"Length matters: Clustering system log messages using length of words. arXiv preprint arXiv:1611.03213","author":"Shima Keiichi","year":"2016","unstructured":"Keiichi Shima. 2016. Length matters: Clustering system log messages using length of words. arXiv preprint arXiv:1611.03213 (2016)."},{"key":"e_1_2_1_82_1","unstructured":"Yicheng Sui Yuzhe Zhang Jianjun Sun Ting Xu Shenglin Zhang Zhengdan Li Yongqian Sun Fangrui Guo Junyu Shen Yuzhi Zhang et al. 2023. LogKG: Log Failure Diagnosis through Knowledge Graph. IEEE Transactions on Services Computing (2023)."},{"key":"e_1_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543146.3543168"},{"key":"e_1_2_1_84_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588938"},{"key":"e_1_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPOM.2003.1251233"},{"key":"e_1_2_1_87_1","volume-title":"Attention is all you need. Advances in neural information processing systems 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. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549113"},{"key":"e_1_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549176"},{"key":"e_1_2_1_90_1","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 8696--8708","author":"Joty Shafiq","unstructured":"YueWang,WeishiWang, Shafiq Joty, and Steven C.H. Hoi. 2021. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 8696--8708."},{"key":"e_1_2_1_91_1","doi-asserted-by":"crossref","unstructured":"Jason Wei and Kai Zou. 2019. EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks. 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 6382--6388.","DOI":"10.18653\/v1\/D19-1670"},{"key":"e_1_2_1_92_1","volume-title":"Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush.","author":"Wolf Thomas","year":"2020","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online, 38--45."},{"key":"e_1_2_1_93_1","volume-title":"Clear: Contrastive learning for sentence representation. arXiv preprint arXiv:2012.15466","author":"Wu Zhuofeng","year":"2020","unstructured":"Zhuofeng Wu, Sinong Wang, Jiatao Gu, Madian Khabsa, Fei Sun, and Hao Ma. 2020. Clear: Contrastive learning for sentence representation. arXiv preprint arXiv:2012.15466 (2020)."},{"key":"e_1_2_1_94_1","volume-title":"DivLog: Log Parsing with Prompt Enhanced In-Context Learning. In 2024 IEEE\/ACM 46th International Conference on Software Engineering (ICSE). IEEE Computer Society, 983--983","author":"Xu Junjielong","year":"2024","unstructured":"Junjielong Xu, Ruichun Yang, Yintong Huo, Chengyu Zhang, and Pinjia He. 2024. DivLog: Log Parsing with Prompt Enhanced In-Context Learning. In 2024 IEEE\/ACM 46th International Conference on Software Engineering (ICSE). IEEE Computer Society, 983--983."},{"key":"e_1_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629575.1629587"},{"key":"e_1_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649506"},{"key":"e_1_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00130"},{"key":"e_1_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338931"},{"key":"e_1_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3473919"},{"key":"e_1_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00021"},{"key":"e_1_2_1_101_1","volume-title":"Unilog: Deploy one model and specialize it for all log analysis tasks. arXiv preprint arXiv:2112.03159","author":"Zhu Yichen","year":"2021","unstructured":"Yichen Zhu, Weibin Meng, Ying Liu, Shenglin Zhang, Tao Han, Shimin Tao, and Dan Pei. 2021. Unilog: Deploy one model and specialize it for all log analysis tasks. arXiv preprint arXiv:2112.03159 (2021)."}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654966","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3654966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T14:41:50Z","timestamp":1755787310000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654966"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,29]]},"references-count":101,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,5,29]]}},"alternative-id":["10.1145\/3654966"],"URL":"https:\/\/doi.org\/10.1145\/3654966","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,29]]}}}