{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:15:50Z","timestamp":1743124550849,"version":"3.40.3"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031434204"},{"type":"electronic","value":"9783031434211"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43421-1_5","type":"book-chapter","created":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T20:37:24Z","timestamp":1694983044000},"page":"71-89","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["KL Regularized Normalization Framework for\u00a0Low Resource Tasks"],"prefix":"10.1007","author":[{"given":"Neeraj","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankur","family":"Narang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brejesh","family":"Lall","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,18]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Asperti, A., Trentin, M.: Balancing reconstruction error and kullback-leibler divergence in variational autoencoders (2020)","DOI":"10.1109\/ACCESS.2020.3034828"},{"key":"5_CR2","unstructured":"Ba, J., Kiros, J., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"5_CR3","unstructured":"Baevski, A., Zhou, H., Rahman Mohamed, A., Auli, M.: wav2vec 2.0: A framework for self-supervised learning of speech representations. arXiv preprint arXiv:2006.11477 (2020)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Belinkov, Y., Poliak, A., Shieber, S., Durme, B.V., Rush, A.M.: On adversarial removal of hypothesis-only bias in natural language inference. In: Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (SEMEVAL) (2019)","DOI":"10.18653\/v1\/S19-1028"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Bowman, S., Vilnis, L., Vinyals, O., Dai, A., Jozefowicz, R., Bengio, S.: Generating sentences from a continuous space. In: Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) (2016)","DOI":"10.18653\/v1\/K16-1002"},{"key":"5_CR6","unstructured":"Chaudhari, P., et al.: Entropy-SGD: biasing gradient descent into wide valleys. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24\u201326 April 2017, Conference Track Proceedings (2017)"},{"key":"5_CR7","unstructured":"Cooijmans, T., Ballas, N., Laurent, C., Courville, A.C.: Recurrent batch normalization. arXiv preprint arXiv:1603.09025 (2017)"},{"key":"5_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: 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 (NAACL) (2019)"},{"key":"5_CR9","unstructured":"Devries, T., Taylor, G.W.: Learning confidence for out-of-distribution detection in neural networks. arXiv preprint arXiv:1802.04865 (2018)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Elazar, Y., Goldberg, Y.: Adversarial removal of demographic attributes from text data. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2018)","DOI":"10.18653\/v1\/D18-1002"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Fan, Z., Li, M., Zhou, S., Xu, B.: Exploring wav2vec 2.0 on speaker verification and language identification. arXiv preprint arXiv:2012.06185 (2021)","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"5_CR12","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096\u20132030 (2016). http:\/\/dl.acm.org\/citation.cfm?id=2946645.2946704"},{"key":"5_CR13","unstructured":"Gong, Y., Luo, H., Zhang, J.: Natural language inference over interaction space. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"5_CR14","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http:\/\/www.deeplearningbook.org"},{"key":"5_CR15","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems. vol. 27, pp. 2672\u20132680 (2014)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Gururangan, S., Swayamdipta, S., Levy, O., Schwartz, R., Bowman, S., Smith, N.A.: Annotation artifacts in natural language inference data. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) (2018)","DOI":"10.18653\/v1\/N18-2017"},{"key":"5_CR17","unstructured":"Hannun, A.Y., et al.: Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Hao, Y., Dong, L., Wei, F., Xu, K.: Visualizing and understanding the effectiveness of BERT. 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), pp. 4141\u20134150. Association for Computational Linguistics, Hong Kong, China (Nov 2019)","DOI":"10.18653\/v1\/D19-1424"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.J.: Arbitrary style transfer in real-time with adaptive instance normalization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1510\u20131519 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"5_CR20","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)"},{"key":"5_CR21","unstructured":"Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization. In: Silva, R., Globerson, A., Globerson, A. (eds.) 34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018, pp. 876\u2013885. 34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018, Association For Uncertainty in Artificial Intelligence (AUAI) (2018)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Jia, S., Chen, D.J., Chen, H.T.: Instance-level meta normalization. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4860\u20134868 (2019)","DOI":"10.1109\/CVPR.2019.00500"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Khot, T., Sabharwal, A., Clark, P.: SciTaiL: a textual entailment dataset from science question answering. In: AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12022"},{"key":"5_CR24","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Kim, T., Song, I., Bengio, Y.: Dynamic layer normalization for adaptive neural acoustic modeling in speech recognition. arXiv preprint arXiv:1707.06065 (2017)","DOI":"10.21437\/Interspeech.2017-556"},{"key":"5_CR26","unstructured":"Kliger, M., Fleishman, S.: Novelty detection with GAN. arXiv preprint arXiv:1802.10560 (2018)"},{"key":"5_CR27","unstructured":"Kou, Z., You, K., Long, M., Wang, J.: Stochastic normalization. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"5_CR28","unstructured":"Krogh, A., Hertz, J.A.: A simple weight decay can improve generalization. In: Advances in Neural Information Processing Systems (NeurIPS) (1992)"},{"key":"5_CR29","unstructured":"Lai, A., Bisk, Y., Hockenmaier, J.: Natural language inference from multiple premises. In: Proceedings of the Eighth International Joint Conference on Natural Language Processing (IJCNLP) (2017)"},{"key":"5_CR30","unstructured":"Lee, C., Cho, K., Kang, W.: Mixout: Effective regularization to finetune large-scale pretrained language models. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"5_CR31","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1109\/TPAMI.2019.2932062","volume":"43","author":"P Luo","year":"2021","unstructured":"Luo, P., Zhang, R., Ren, J., Peng, Z., Li, J.: Switchable normalization for learning-to-normalize deep representation. IEEE Trans. Pattern Anal. Mach. Intell. 43, 712\u2013728 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR32","unstructured":"Mahabadi, K.R., Belinkov, Y., Henderson, J.: End-to-end bias mitigation by modelling biases in corpora. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL) (2020)"},{"key":"5_CR33","unstructured":"Marelli, M., Menini, S., Baroni, M., Bentivogli, L., Bernardi, R., Zamparelli, R.: A SICK cure for the evaluation of compositional distributional semantic models. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC) (2014)"},{"key":"5_CR34","unstructured":"Mosbach, M., Andriushchenko, M., Klakow, D.: On the stability of fine-tuning BERT: misconceptions, explanations, and strong baselines. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"5_CR35","unstructured":"Nam, H., Kim, H.E.: Batch-instance normalization for adaptively style-invariant neural networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Nesterov, Y.: Introductory lectures on convex optimization - a basic course. In: Applied Optimization (2004)","DOI":"10.1007\/978-1-4419-8853-9"},{"key":"5_CR37","unstructured":"Niranjan, A., Sharma, M.C., Gutha, S.B.C., Shaik, M.A.B.: End-to-end whisper to natural speech conversion using modified transformer network (2021)"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Pavlick, E., Callison-Burch, C.: Most \u201cbabies\u201d are \u201clittle\u201d and most \u201cproblems\u201d are \u201chuge\u201d: Compositional entailment in adjective-nouns. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL) (2016)","DOI":"10.18653\/v1\/P16-1204"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Pavlick, E., Wolfe, T., Rastogi, P., Callison-Burch, C., Dredze, M., Van Durme, B.: Framenet+: Fast paraphrastic tripling of frameNet. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL) (2015)","DOI":"10.3115\/v1\/P15-2067"},{"key":"5_CR41","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"5_CR42","unstructured":"Rahman, A., Ng, V.: Resolving complex cases of definite pronouns: the winograd schema challenge. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing (EMNPL) (2012)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Reisinger, D., Rudinger, R., Ferraro, F., Harman, C., Rawlins, K., Van Durme, B.: Semantic proto-roles. In: Transactions of the Association for Computational Linguistics (TACL) (2015)","DOI":"10.1162\/tacl_a_00152"},{"key":"5_CR44","unstructured":"Salimans, T., Kingma, D.P.: Weight normalization: A simple reparameterization to accelerate training of deep neural networks. In: Advances in Neural Information Processing Systems (NIPS) (2016)"},{"key":"5_CR45","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. In: Journal of Machine Learning Research (JMLR) (2014)"},{"key":"5_CR46","doi-asserted-by":"publisher","unstructured":"Tan, S., Zhang, J.: An empirical study of sentiment analysis for Chinese documents. Expert Syst. Appl. 34(4), 2622\u20132629 (2008). https:\/\/doi.org\/10.1016\/j.eswa.2007.05.028, http:\/\/dx.doi.org\/10.1016\/j.eswa.2007.05.028","DOI":"10.1016\/j.eswa.2007.05.028"},{"key":"5_CR47","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)"},{"key":"5_CR48","doi-asserted-by":"crossref","unstructured":"Wang, Z., Hamza, W., Florian, R.: Bilateral multi-perspective matching for natural language sentences. In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI) (2017)","DOI":"10.24963\/ijcai.2017\/579"},{"key":"5_CR49","unstructured":"White, A.S., Rastogi, P., Duh, K., Van Durme, B.: Inference is everything: recasting semantic resources into a unified evaluation framework. In: Proceedings of the Eighth International Joint Conference on Natural Language Processing (IJCNLP) (2017)"},{"key":"5_CR50","unstructured":"Wolf, T., et al.: HuggingFace\u2019s transformers: state-of-the-art natural language processing. arXiv:1910.03771 (2019)"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K.: Group normalization. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Yadav, H., Gupta, A., Rallabandi, S.K., Black, A.W., Shah, R.R.: Intent classification using pre-trained embeddings for low resource languages (2021)","DOI":"10.21437\/Interspeech.2022-10873"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, S., Rudinger, R., Duh, K., Van Durme, B.: Ordinal common-sense inference. In: TACL (2017)","DOI":"10.1162\/tacl_a_00068"},{"key":"5_CR54","unstructured":"Zhang, T., Wu, F., Katiyar, A., Weinberger, K.Q., Artzi, Y.: Revisiting few-sample BERT fine-tuning. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"5_CR55","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vis. 130, 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vis."},{"key":"5_CR56","doi-asserted-by":"crossref","unstructured":"Zoph, B., Yuret, D., May, J., Knight, K.: Transfer learning for low-resource neural machine translation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1568\u20131575. Association for Computational Linguistics, Austin, Texas (Nov 2016)","DOI":"10.18653\/v1\/D16-1163"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43421-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T20:42:12Z","timestamp":1694983332000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43421-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434204","9783031434211"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43421-1_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"18 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"829","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"196","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.63","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted papers.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}