{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:12:32Z","timestamp":1743059552464,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819723867"},{"type":"electronic","value":"9789819723874"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-97-2387-4_11","type":"book-chapter","created":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T18:02:02Z","timestamp":1714240922000},"page":"159-173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DADR: A Denoising Approach for\u00a0Dense Retrieval Model Training"],"prefix":"10.1007","author":[{"given":"Mengxue","family":"Du","sequence":"first","affiliation":[]},{"given":"Shasha","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Huijun","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Miaomiao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Ji","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,28]]},"reference":[{"key":"11_CR1","unstructured":"Arazo, E., Ortego, D., Albert, P., O\u2019Connor, N.E., McGuinness, K.: Unsupervised label noise modeling and loss correction (2019)"},{"key":"11_CR2","unstructured":"Arazo, E., Ortego, D., Albert, P., O\u2019Connor, N., McGuinness, K.: Unsupervised label noise modeling and loss correction. In: International Conference on Machine Learning, pp. 312\u2013321. PMLR (2019)"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Brodley, C.E., Friedl, M.A.: Identifying mislabeled training data (1999)","DOI":"10.1613\/jair.606"},{"key":"11_CR4","unstructured":"Burges, C.J.C.: From ranknet to lambdarank to lambdamart: an overview (2010)"},{"key":"11_CR5","doi-asserted-by":"publisher","unstructured":"Chen, Y., Zhou, D., Li, L., Han, J.M.: Multimodal encoders for food-oriented cross-modal retrieval. In: U, L.H., Spaniol, M., Sakurai, Y., Chen, J. (eds.) Web and Big Data. APWeb-WAIM 2021. LNCS, vol. 12859, pp. 253\u2013266. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-85899-5_19","DOI":"10.1007\/978-3-030-85899-5_19"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, M., et al.: Vista: vision and scene text aggregation for cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5184\u20135193 (2022)","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Craswell, N., Mitra, B., Yilmaz, E., Campos, D., Voorhees, E.M.: Overview of the Trec 2019 deep learning track. Text REtrieval Conference (2020)","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"key":"11_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (2018)"},{"key":"11_CR9","doi-asserted-by":"publisher","unstructured":"Du, M., et al.: Topic-grained text representation-based model for document retrieval. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds.) Artificial Neural Networks and Machine Learning. ICANN 2022. LNCS, vol. 13531, pp. 776\u2013788. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15934-3_64","DOI":"10.1007\/978-3-031-15934-3_64"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Gao, L., Dai, Z., Fan, Z., Callan, J.: Complementing lexical retrieval with semantic residual embedding. Cornell University - arXiv (2020)","DOI":"10.1007\/978-3-030-72113-8_10"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Gao, Y., et al.: Self-guided learning to denoise for robust recommendation (2022)","DOI":"10.1145\/3477495.3532059"},{"key":"11_CR12","unstructured":"Gutmann, M.U., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: International Conference on Artificial Intelligence and Statistics (2010)"},{"key":"11_CR13","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.W.: Realm: retrieval-augmented language model pre-training. arXiv : Computation and Language (2020)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Huang, J., Qu, L., Jia, R., Zhao, B.: O2u-net: a simple noisy label detection approach for deep neural networks (2019)","DOI":"10.1109\/ICCV.2019.00342"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Huang, J.T., et al.: Embedding-based retrieval in Facebook search (2020)","DOI":"10.1145\/3394486.3403305"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6769\u20136781 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. arXiv : Computation and Language (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Khattab, O., Zaharia, M.: Colbert: efficient and effective passage search via contextualized late interaction over bert. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 39\u201348 (2020)","DOI":"10.1145\/3397271.3401075"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Kim, D., Koo, J., Kim, U.M.: Osp-class: open set pseudo-labeling with noise robust training for text classification. In: 2022 IEEE International Conference on Big Data (Big Data), pp. 5520\u20135529. IEEE (2022)","DOI":"10.1109\/BigData55660.2022.10020273"},{"key":"11_CR20","unstructured":"Li, J., Socher, R., Hoi, S.C.H.: Dividemix: learning with noisy labels as semi-supervised learning. arXiv : Computer Vision and Pattern Recognition (2020)"},{"key":"11_CR21","unstructured":"Li, Y., Liu, S., She, Q., Mcleod, A., Wang, B.: On learning contrastive representations for learning with noisy labels (2023)"},{"key":"11_CR22","unstructured":"Northcutt, C.G., Jiang, L., Chuang, I.L.: Confident learning: estimating uncertainty in dataset labels. arXiv : Machine Learning (2019)"},{"key":"11_CR23","unstructured":"Parker, B., Sokolov, A., Ahmed, M., Kalebic, M., Akinli\u00a0Kocak, S., Shai, O.: Domain specific fine-tuning of denoising sequence-to-sequence models for natural language summarization. arXiv e-prints pp. arXiv\u20132204 (2022)"},{"key":"11_CR24","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. Neural Inf. Process. Syst. (2019)"},{"key":"11_CR25","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Qu, Y., et al.: Rocketqa: an optimized training approach to dense passage retrieval for open-domain question answering (2020)","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Ren, R., et al.: Rocketqav2: a joint training method for dense passage retrieval and passage re-ranking. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 2825\u20132835 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.224"},{"key":"11_CR28","unstructured":"Toneva, M., Sordoni, A., des Combes, R.T., Trischler, A., Bengio, Y., Gordon, G.J.: An empirical study of example forgetting during deep neural network learning. In: International Conference on Learning Representations (2018)"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Wang, W., Feng, F., He, X., Nie, L., Chua, T.S.: Denoising implicit feedback for recommendation. arXiv : Information Retrieval (2020)","DOI":"10.1145\/3437963.3441800"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Zhan, J., Mao, J., Liu, Y., Guo, J., Zhang, M., Ma, S.: Optimizing dense retrieval model training with hard negatives. Cornell University - arXiv (2021)","DOI":"10.1145\/3404835.3462880"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2387-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T05:35:57Z","timestamp":1731821757000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2387-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819723867","9789819723874"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2387-4_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apweb-waim2023.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}