{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:29:43Z","timestamp":1778693383899,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"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":[[2024,10,8]]},"DOI":"10.1145\/3640457.3688108","type":"proceedings-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T15:39:28Z","timestamp":1728401968000},"page":"601-611","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["ConFit: Improving Resume-Job Matching using Data Augmentation and Contrastive Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0924-6432","authenticated-orcid":false,"given":"Xiao","family":"Yu","sequence":"first","affiliation":[{"name":"Computer Science, Columbia University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7026-1300","authenticated-orcid":false,"given":"Jinzhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Intellipro Group Inc., China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1524-5890","authenticated-orcid":false,"given":"Zhou","family":"Yu","sequence":"additional","affiliation":[{"name":"Columbia University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Shuqing Bian Xu Chen Wayne\u00a0Xin Zhao Kun Zhou Yupeng Hou Yang Song Tao Zhang and Ji-Rong Wen. 2020. Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network. arxiv:2009.13299\u00a0[cs.CL]","DOI":"10.1145\/3340531.3411929"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_3_1","unstructured":"Tolga Bolukbasi Kai-Wei Chang James Zou Venkatesh Saligrama and Adam Kalai. 2016. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. arxiv:1607.06520\u00a0[cs.CL]"},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a097)","author":"Brunet Marc-Etienne","year":"2019","unstructured":"Marc-Etienne Brunet, Colleen Alkalay-Houlihan, Ashton Anderson, and Richard Zemel. 2019. Understanding the Origins of Bias in Word Embeddings. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 803\u2013811. https:\/\/proceedings.mlr.press\/v97\/brunet19a.html"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534162"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Jan Cegin Jakub Simko and Peter Brusilovsky. 2023. ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness. arxiv:2305.12947\u00a0[cs.CL]","DOI":"10.18653\/v1\/2023.emnlp-main.117"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_2_8_1","unstructured":"Ting Chen Simon Kornblith Mohammad Norouzi and Geoffrey Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. arxiv:2002.05709\u00a0[cs.LG]"},{"key":"e_1_3_2_2_9_1","unstructured":"Pengyu Cheng Weituo Hao Siyang Yuan Shijing Si and Lawrence Carin. 2021. FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders. arxiv:2103.06413\u00a0[cs.CL]"},{"key":"e_1_3_2_2_10_1","volume-title":"Unsupervised Cross-lingual Representation Learning at Scale. CoRR abs\/1911.02116","author":"Conneau Alexis","year":"2019","unstructured":"Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzm\u00e1n, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Unsupervised Cross-lingual Representation Learning at Scale. CoRR abs\/1911.02116 (2019). arXiv:1911.02116http:\/\/arxiv.org\/abs\/1911.02116"},{"key":"e_1_3_2_2_11_1","unstructured":"Haixing Dai Zhengliang Liu Wenxiong Liao Xiaoke Huang Yihan Cao Zihao Wu Lin Zhao Shaochen Xu Wei Liu Ninghao Liu Sheng Li Dajiang Zhu Hongmin Cai Lichao Sun Quanzheng Li Dinggang Shen Tianming Liu and Xiang Li. 2023. AugGPT: Leveraging ChatGPT for Text Data Augmentation. arxiv:2302.13007\u00a0[cs.CL]"},{"key":"e_1_3_2_2_12_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arxiv:1810.04805\u00a0[cs.CL]","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. arxiv:1810.04805\u00a0[cs.CL]"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICACITE53722.2022.9823730"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1049"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.04.013"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_19_1","volume-title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels. arxiv:1804.06872\u00a0[cs.LG]","author":"Han Bo","year":"2018","unstructured":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, and Masashi Sugiyama. 2018. Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels. arxiv:1804.06872\u00a0[cs.LG]"},{"key":"e_1_3_2_2_20_1","volume-title":"LinkedIn Usage and Revenue Statistics","author":"Iqbal Mansoor","year":"2023","unstructured":"Mansoor Iqbal. 2023. LinkedIn Usage and Revenue Statistics (2023). a. https:\/\/www.businessofapps.com\/data\/linkedin-statistics\/ Accessed: 2023-12-29."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","unstructured":"Gautier Izacard Mathilde Caron Lucas Hosseini Sebastian Riedel Piotr Bojanowski Armand Joulin and Edouard Grave. 2021. Unsupervised Dense Information Retrieval with Contrastive Learning. https:\/\/doi.org\/10.48550\/ARXIV.2112.09118","DOI":"10.48550\/ARXIV.2112.09118"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Junshu Jiang Songyun Ye Wei Wang Jingran Xu and Xiaosheng Luo. 2020. Learning Effective Representations for Person-Job Fit by Feature Fusion. arxiv:2006.07017\u00a0[cs.IR]","DOI":"10.1145\/3340531.3412717"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Mandar Joshi Eunsol Choi Daniel\u00a0S. Weld and Luke Zettlemoyer. 2017. TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension. arxiv:1705.03551\u00a0[cs.CL]","DOI":"10.18653\/v1\/P17-1147"},{"key":"e_1_3_2_2_26_1","unstructured":"Ehsan Kamalloo Nandan Thakur Carlos Lassance Xueguang Ma Jheng-Hong Yang and Jimmy Lin. 2023. Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard. arxiv:2306.07471\u00a0[cs.IR]"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Vladimir Karpukhin Barlas O\u011fuz Sewon Min Patrick Lewis Ledell Wu Sergey Edunov Danqi Chen and Wen tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. arxiv:2004.04906\u00a0[cs.CL]","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_2_28_1","volume-title":"Natural Questions: a Benchmark for Question Answering Research. Transactions of the Association of Computational Linguistics","author":"Kwiatkowski Tom","year":"2019","unstructured":"Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Matthew Kelcey, Jacob Devlin, Kenton Lee, Kristina\u00a0N. Toutanova, Llion Jones, Ming-Wei Chang, Andrew Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. Natural Questions: a Benchmark for Question Answering Research. Transactions of the Association of Computational Linguistics (2019)."},{"key":"e_1_3_2_2_29_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\u00a0[cs.CL]"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3186942"},{"key":"e_1_3_2_2_31_1","unstructured":"Eran Malach and Shai Shalev-Shwartz. 2018. Decoupling \"when to update\" from \"how to update\". arxiv:1706.02613\u00a0[cs.LG]"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1063"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSCSS57650.2023.10169716"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2210.07316"},{"key":"e_1_3_2_2_35_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. CoRR abs\/1611.09268","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. CoRR abs\/1611.09268 (2016). arxiv:1611.09268http:\/\/arxiv.org\/abs\/1611.09268"},{"key":"e_1_3_2_2_36_1","unstructured":"OpenAI. 2022. New and improved embedding model. https:\/\/openai.com\/blog\/new-and-improved-embedding-model"},{"key":"e_1_3_2_2_37_1","unstructured":"OpenAI. 2022. OpenAI: Introducing ChatGPT. https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_3_2_2_38_1","unstructured":"Keiron O\u2019Shea and Ryan Nash. 2015. An Introduction to Convolutional Neural Networks. arxiv:1511.08458\u00a0[cs.NE]"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210025"},{"key":"e_1_3_2_2_40_1","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. arxiv:2103.00020\u00a0[cs.CV]"},{"key":"e_1_3_2_2_41_1","volume-title":"BPR: Bayesian Personalized Ranking from Implicit Feedback. arxiv:1205.2618\u00a0[cs.IR]","author":"Rendle Steffen","year":"2012","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2012. BPR: Bayesian Personalized Ranking from Implicit Feedback. arxiv:1205.2618\u00a0[cs.IR]"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3573128.3609347"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00434"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","unstructured":"Taihua Shao Chengyu Song Jianming Zheng Fei Cai and Honghui Chen. 2023. Exploring Internal and External Interactions for Semi-Structured Multivariate Attributes in Job-Resume Matching. In International Journal of Intelligent Systems. https:\/\/doi.org\/10.1155\/2023\/2994779","DOI":"10.1155\/2023"},{"key":"e_1_3_2_2_46_1","volume-title":"Staudemeyer and Eric\u00a0Rothstein Morris","author":"C.","year":"2019","unstructured":"Ralf\u00a0C. Staudemeyer and Eric\u00a0Rothstein Morris. 2019. Understanding LSTM \u2013 a tutorial into Long Short-Term Memory Recurrent Neural Networks. arxiv:1909.09586\u00a0[cs.NE]"},{"key":"e_1_3_2_2_47_1","volume-title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models. arxiv:2104.08663\u00a0[cs.IR]","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models. arxiv:2104.08663\u00a0[cs.IR]"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2682862.2682863"},{"key":"e_1_3_2_2_49_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van\u00a0der Maaten Laurens","year":"2008","unstructured":"Laurens van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research 9, 86 (2008), 2579\u20132605. http:\/\/jmlr.org\/papers\/v9\/vandermaaten08a.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_50_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. arxiv:1706.03762\u00a0[cs.CL]"},{"key":"e_1_3_2_2_51_1","unstructured":"Liang Wang Nan Yang Xiaolong Huang Binxing Jiao Linjun Yang Daxin Jiang Rangan Majumder and Furu Wei. 2022. Text Embeddings by Weakly-Supervised Contrastive Pre-training. arxiv:2212.03533\u00a0[cs.CL]"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.125"},{"key":"e_1_3_2_2_53_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 6383\u20136389. https:\/\/www.aclweb.org\/anthology\/D19-1670","DOI":"10.18653\/v1\/D19-1670"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330963"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"crossref","unstructured":"Chen Yang Yupeng Hou Yang Song Tao Zhang Ji-Rong Wen and Wayne\u00a0Xin Zhao. 2022. Modeling Two-Way Selection Preference for Person-Job Fit. In RecSys.","DOI":"10.1145\/3523227.3546752"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04775-2"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Chen Zhu Hengshu Zhu Hui Xiong Chao Ma Fang Xie Pengliang Ding and Pan Li. 2018. Person-Job Fit: Adapting the Right Talent for the Right Job with Joint Representation Learning. arxiv:1810.04040\u00a0[cs.IR]","DOI":"10.1145\/3234465"}],"event":{"name":"RecSys '24: 18th ACM Conference on Recommender Systems","location":"Bari Italy","acronym":"RecSys '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["18th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688108","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640457.3688108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:29Z","timestamp":1750294709000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":57,"alternative-id":["10.1145\/3640457.3688108","10.1145\/3640457"],"URL":"https:\/\/doi.org\/10.1145\/3640457.3688108","relation":{},"subject":[],"published":{"date-parts":[[2024,10,8]]},"assertion":[{"value":"2024-10-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}