{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T10:31:11Z","timestamp":1768213871843,"version":"3.49.0"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031703584","type":"print"},{"value":"9783031703591","type":"electronic"}],"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\/978-3-031-70359-1_7","type":"book-chapter","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T04:02:43Z","timestamp":1724904163000},"page":"107-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Low-Hanging Fruit: Knowledge Distillation from\u00a0Noisy Teachers for\u00a0Open Domain Spoken Language Understanding"],"prefix":"10.1007","author":[{"given":"Cheng","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivor W.","family":"Tsang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"7_CR1","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1007\/978-3-319-45510-5_4","volume-title":"Text, Speech, and Dialogue","author":"A Aghaebrahimian","year":"2016","unstructured":"Aghaebrahimian, A., Jur\u010d\u00ed\u010dek, F.: Constraint-based open-domain question answering using knowledge graph search. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2016. LNCS (LNAI), vol. 9924, pp. 28\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-45510-5_4"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Aghaebrahimian, A., Jurc\u00edcek, F.: Open-domain factoid question answering via knowledge graph search. In: Proceedings of the Workshop on Human-Computer Question Answering, pp. 22\u201328 (2016)","DOI":"10.18653\/v1\/W16-0104"},{"key":"7_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR4","unstructured":"Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"7_CR5","unstructured":"Chen, C., Lyu, Y., Tsang, I.W.: Adversary-aware partial label learning with label distillation. arXiv preprint arXiv:2304.00498 (2023)"},{"key":"7_CR6","unstructured":"Chen, C., Tsang, I.: Self-teaching prompting for multi-intent learning with limited supervision. In: The Second Tiny Papers Track at ICLR 2024 (2024). https:\/\/openreview.net\/forum?id=DeoamI1BFh"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chen, D., Yih, W.t.: Open-domain question answering. In: Savary, A., Zhang, Y. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts, pp. 34\u201337. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.acl-tutorials.8"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, H., Shen, Y., Liu, X., He, P., Chen, W., Gao, J.: UnitedQA: a hybrid approach for open domain question answering. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 3080\u20133090. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-long.240"},{"key":"7_CR9","unstructured":"Coucke, A., et\u00a0al.: Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. arXiv preprint arXiv:1805.10190 (2018)"},{"key":"7_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"7_CR11","unstructured":"Diao, S., Wang, P., Lin, Y., Zhang, T.: Active prompting with chain-of-thought for large language models (2023)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Fei, Y., Nie, P., Meng, Z., Wattenhofer, R., Sachan, M.: Beyond prompting: making pre-trained language models better zero-shot learners by clustering representations. arXiv preprint arXiv:2210.16637 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.587"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Gangadharaiah, R., Narayanaswamy, B.: Joint multiple intent detection and slot labeling for goal-oriented dialog. 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), pp. 564\u2013569. Association for Computational Linguistics, Minneapolis, Minnesota (2019)","DOI":"10.18653\/v1\/N19-1055"},{"key":"7_CR14","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. Int. J. Comput. Vision 129, 1789\u20131819 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"7_CR15","unstructured":"Gunel, B., Du, J., Conneau, A., Stoyanov, V.: Supervised contrastive learning for pre-trained language model fine-tuning. arXiv preprint arXiv:2011.01403 (2020)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Hemphill, C.T., Godfrey, J.J., Doddington, G.R.: The Atis spoken language systems pilot corpus. In: Speech and Natural Language: Proceedings of a Workshop Held at Hidden Valley, Pennsylvania, June 24\u201327, 1990 (1990)","DOI":"10.3115\/116580.116613"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Heo, B., Lee, M., Yun, S., Choi, J.Y.: Knowledge transfer via distillation of activation boundaries formed by hidden neurons. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 3779\u20133787 (2019)","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"7_CR18","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"7_CR19","unstructured":"Hu, E.J., et al.: Amortizing intractable inference in large language models. arXiv preprint arXiv:2310.04363 (2023)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"7_CR21","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: Advances in Neural Information Processing Systems, vol. 33, 18661\u201318673 (2020)"},{"key":"7_CR22","unstructured":"Khosla, P., et al.: Supervised contrastive learning. CoRR abs\/2004.11362 (2020)"},{"key":"7_CR23","doi-asserted-by":"publisher","first-page":"11377","DOI":"10.1007\/s11042-016-3724-4","volume":"76","author":"B Kim","year":"2017","unstructured":"Kim, B., Ryu, S., Lee, G.G.: Two-stage multi-intent detection for spoken language understanding. Multimedia Tools Appl. 76, 11377\u201311390 (2017)","journal-title":"Multimedia Tools Appl."},{"key":"7_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"7_CR25","unstructured":"Liu, J., et al.: Generated knowledge prompting for commonsense reasoning. arXiv preprint arXiv:2110.08387 (2021)"},{"issue":"11","key":"7_CR26","doi-asserted-by":"publisher","first-page":"7955","DOI":"10.1109\/TPAMI.2021.3119334","volume":"44","author":"W Liu","year":"2021","unstructured":"Liu, W., Wang, H., Shen, X., Tsang, I.W.: The emerging trends of multi-label learning. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7955\u20137974 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR27","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Knowledge distillation via instance relationship graph. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7096\u20137104 (2019)","DOI":"10.1109\/CVPR.2019.00726"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yu, X., Fang, Y., Zhang, X.: Graphprompt: unifying pre-training and downstream tasks for graph neural networks. In: Proceedings of the ACM Web Conference 2023 (2023)","DOI":"10.1145\/3543507.3583386"},{"key":"7_CR30","unstructured":"Malkinski, M., Mandziuk, J.: Multi-label contrastive learning for abstract visual reasoning. CoRR abs\/2012.01944 (2020). https:\/\/arxiv.org\/abs\/2012.01944"},{"key":"7_CR31","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"7_CR32","unstructured":"OpenAI: Gpt-4 technical report (2023)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., Cho, M.: Relational knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3967\u20133976 (2019)","DOI":"10.1109\/CVPR.2019.00409"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Qin, L., Wei, F., Xie, T., Xu, X., Che, W., Liu, T.: GL-GIN: fast and accurate non-autoregressive model for joint multiple intent detection and slot filling. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 178\u2013188. Association for Computational Linguistics, Online (2021)","DOI":"10.18653\/v1\/2021.acl-long.15"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Qin, L., Xu, X., Che, W., Liu, T.: AGIF: an adaptive graph-interactive framework for joint multiple intent detection and slot filling. arXiv preprint arXiv:2004.10087 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.163"},{"key":"7_CR36","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Su, X., Wang, R., Dai, X.: Contrastive learning-enhanced nearest neighbor mechanism for multi-label text classification. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 672\u2013679. Association for Computational Linguistics, Dublin, Ireland (2022)","DOI":"10.18653\/v1\/2022.acl-short.75"},{"key":"7_CR38","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. arXiv preprint arXiv:1910.10699 (2019)"},{"key":"7_CR39","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1365\u20131374 (2019)","DOI":"10.1109\/ICCV.2019.00145"},{"key":"7_CR41","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"7_CR42","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)"},{"key":"7_CR43","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"7_CR44","unstructured":"Xing, B., Tsang, I.W.: Co-guiding net: aarXiv preprint arXiv:2210.10375 (2022)"},{"key":"7_CR45","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: XLNet: generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"7_CR46","unstructured":"Yao, S., et al.: React: synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022)"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7130\u20137138 (2017)","DOI":"10.1109\/CVPR.2017.754"},{"issue":"5","key":"7_CR48","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/JPROC.2012.2225812","volume":"101","author":"S Young","year":"2013","unstructured":"Young, S., Ga\u0161i\u0107, M., Thomson, B., Williams, J.D.: Pomdp-based statistical spoken dialog systems: A review. Proc. IEEE 101(5), 1160\u20131179 (2013)","journal-title":"Proc. IEEE"},{"key":"7_CR49","unstructured":"Zhou, Y., et al.: Large language models are human-level prompt engineers. arXiv preprint arXiv:2211.01910 (2022)"}],"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\/978-3-031-70359-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T07:27:32Z","timestamp":1768202852000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70359-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703584","9783031703591"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70359-1_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","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":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}