{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:13Z","timestamp":1750219753952,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T00:00:00Z","timestamp":1697846400000},"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":[[2023,10,21]]},"DOI":"10.1145\/3583780.3615093","type":"proceedings-article","created":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T07:45:26Z","timestamp":1697874326000},"page":"326-336","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6244-2931","authenticated-orcid":false,"given":"Xuxin","family":"Cheng","sequence":"first","affiliation":[{"name":"Peking University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3371-0137","authenticated-orcid":false,"given":"Wanshi","family":"Xu","sequence":"additional","affiliation":[{"name":"Peking University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4530-5516","authenticated-orcid":false,"given":"Zhihong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Peking University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7710-8835","authenticated-orcid":false,"given":"Hongxiang","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0144-1794","authenticated-orcid":false,"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[{"name":"Peking University, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1309"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Jane Bromley Isabelle Guyon Yann LeCun and etal 1993. Signature verification using a \"Siamese\" time delay neural network. Advances in Neural Information Processing Systems (1993).  Jane Bromley Isabelle Guyon Yann LeCun and et al. 1993. Signature verification using a \"Siamese\" time delay neural network. Advances in Neural Information Processing Systems (1993).","DOI":"10.1142\/9789812797926_0003"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-781"},{"key":"e_1_3_2_1_4_1","volume-title":"Joint Multiple Intent Detection and Slot Filling Via Self-Distillation. In ICASSP 2022--2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 7612--7616","author":"Chen Lisong","year":"2022","unstructured":"Lisong Chen , Peilin Zhou , and Yuexian Zou . 2022 . Joint Multiple Intent Detection and Slot Filling Via Self-Distillation. In ICASSP 2022--2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 7612--7616 . Lisong Chen, Peilin Zhou, and Yuexian Zou. 2022. Joint Multiple Intent Detection and Slot Filling Via Self-Distillation. In ICASSP 2022--2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 7612--7616."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. 702--703","author":"Chen Xinlei","year":"2020","unstructured":"Xinlei Chen and Kaiming He . 2020 . Improved baselines with momentum contrastive learning . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. 702--703 . Xinlei Chen and Kaiming He. 2020. Improved baselines with momentum contrastive learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. 702--703."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846288"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482229"},{"key":"e_1_3_2_1_8_1","volume-title":"Capture Salient Historical Information: A Fast and Accurate Non-Autoregressive Model for Multi-Turn Spoken Language Understanding. ACM Transactions on Information Systems","author":"Cheng Lizhi","year":"2022","unstructured":"Lizhi Cheng , Weijia Jia , and Wenmian Yang . 2022a. Capture Salient Historical Information: A Fast and Accurate Non-Autoregressive Model for Multi-Turn Spoken Language Understanding. ACM Transactions on Information Systems ( 2022 ). https:\/\/doi.org\/10.1145\/3545800 10.1145\/3545800 Lizhi Cheng, Weijia Jia, and Wenmian Yang. 2022a. Capture Salient Historical Information: A Fast and Accurate Non-Autoregressive Model for Multi-Turn Spoken Language Understanding. ACM Transactions on Information Systems (2022). https:\/\/doi.org\/10.1145\/3545800"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428384"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428384"},{"key":"e_1_3_2_1_11_1","volume-title":"A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding. arXiv preprint arXiv:2211.12220","author":"Cheng Lizhi","year":"2022","unstructured":"Lizhi Cheng , Wenmian Yang , and Weijia Jia . 2022b. A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding. arXiv preprint arXiv:2211.12220 ( 2022 ). Lizhi Cheng, Wenmian Yang, and Weijia Jia. 2022b. A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding. arXiv preprint arXiv:2211.12220 (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219906"},{"key":"e_1_3_2_1_13_1","unstructured":"Alice Coucke Alaa Saade Adrien Ball Th\u00e9odore Bluche Alexandre Caulier David Leroy Cl\u00e9ment Doumouro Thibault Gisselbrecht Francesco Caltagirone Thibaut Lavril etal 2018. Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. arXiv preprint arXiv:1805.10190 (2018).  Alice Coucke Alaa Saade Adrien Ball Th\u00e9odore Bluche Alexandre Caulier David Leroy Cl\u00e9ment Doumouro Thibault Gisselbrecht Francesco Caltagirone Thibaut Lavril et al. 2018. Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. arXiv preprint arXiv:1805.10190 (2018)."},{"key":"e_1_3_2_1_14_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. 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_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1055"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2118"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078634"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 5467--5471","author":"Haihong E","year":"2019","unstructured":"E Haihong , Peiqing Niu , Zhongfu Chen , and Meina Song . 2019 . A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling . In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 5467--5471 . E Haihong, Peiqing Niu, Zhongfu Chen, and Meina Song. 2019. A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 5467--5471."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Dilek Hakkani-T\u00fcr G\u00f6khan T\u00fcr Asli Celikyilmaz Yun-Nung Chen Jianfeng Gao Li Deng and Ye-Yi Wang. 2016. Multi-domain joint semantic frame parsing using bi-directional rnn-lstm.. In Interspeech. 715--719.  Dilek Hakkani-T\u00fcr G\u00f6khan T\u00fcr Asli Celikyilmaz Yun-Nung Chen Jianfeng Gao Li Deng and Ye-Yi Wang. 2016. Multi-domain joint semantic frame parsing using bi-directional rnn-lstm.. In Interspeech. 715--719.","DOI":"10.21437\/Interspeech.2016-402"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3115\/116580.116613"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3724-4"},{"key":"e_1_3_2_1_22_1","volume-title":"Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding. arXiv preprint arXiv:2205.03656","author":"Liang Shining","year":"2022","unstructured":"Shining Liang , Linjun Shou , Jian Pei , Ming Gong , Wanli Zuo , Xianglin Zuo , and Daxin Jiang . 2022. Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding. arXiv preprint arXiv:2205.03656 ( 2022 ). Shining Liang, Linjun Shou, Jian Pei, Ming Gong, Wanli Zuo, Xianglin Zuo, and Daxin Jiang. 2022. Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding. arXiv preprint arXiv:2205.03656 (2022)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1352"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1097"},{"key":"e_1_3_2_1_25_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 b. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019). Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019b. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1214"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.191"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414110"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.15"},{"key":"e_1_3_2_1_30_1","volume-title":"AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling. In Findings of the Association for Computational Linguistics: EMNLP 2020. 1807","author":"Qin Libo","year":"2020","unstructured":"Libo Qin , Xiao Xu , Wanxiang Che , and Ting Liu . 2020 . AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling. In Findings of the Association for Computational Linguistics: EMNLP 2020. 1807 --1816. Libo Qin, Xiao Xu, Wanxiang Che, and Ting Liu. 2020. AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling. In Findings of the Association for Computational Linguistics: EMNLP 2020. 1807--1816."},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Machine Learning. PMLR, 5628--5637","author":"Saunshi Nikunj","year":"2019","unstructured":"Nikunj Saunshi , Orestis Plevrakis , Sanjeev Arora , Mikhail Khodak , and Hrishikesh Khandeparkar . 2019 . A theoretical analysis of contrastive unsupervised representation learning . In International Conference on Machine Learning. PMLR, 5628--5637 . Nikunj Saunshi, Orestis Plevrakis, Sanjeev Arora, Mikhail Khodak, and Hrishikesh Khandeparkar. 2019. A theoretical analysis of contrastive unsupervised representation learning. In International Conference on Machine Learning. PMLR, 5628--5637."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Shen Zhihao","year":"2020","unstructured":"Zhihao Shen , Zhihao Zhang , Hao Zhou , Guodong Long , and Jing Jiang . 2020 . Unsupervised Text Generation via Contrastive Learning . In Proceedings of the AAAI Conference on Artificial Intelligence , Vol. 34 . 9811--9818. Zhihao Shen, Zhihao Zhang, Hao Zhou, Guodong Long, and Jing Jiang. 2020. Unsupervised Text Generation via Contrastive Learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 9811--9818."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.543"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1223--1234","author":"Subramanian Sandeep","year":"2018","unstructured":"Sandeep Subramanian , Adam Trischler , Yoshua Bengio , and Christopher J Pal . 2018 . Learning universal sentence representations with limited supervision . In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1223--1234 . Sandeep Subramanian, Adam Trischler, Yoshua Bengio, and Christopher J Pal. 2018. Learning universal sentence representations with limited supervision. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1223--1234."},{"volume-title":"Spoken language understanding: Systems for extracting semantic information from speech","author":"Tur Gokhan","key":"e_1_3_2_1_35_1","unstructured":"Gokhan Tur and Renato De Mori . 2011. Spoken language understanding: Systems for extracting semantic information from speech . John Wiley & Sons . Gokhan Tur and Renato De Mori. 2011. Spoken language understanding: Systems for extracting semantic information from speech. John Wiley & Sons."},{"key":"e_1_3_2_1_36_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , \u0141ukasz Kaiser , and Illia Polosukhin . 2017. Attention is all you need. Advances in neural information processing systems , Vol. 30 ( 2017 ). Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_37_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Petar Velivc","year":"2017","unstructured":"Petar Velivc kovi\u0107, Guillem Cucurull , Arantxa Casanova , Adriana Romero , Pietro Lio , and Yoshua Bengio . 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 ( 2017 ). Petar Velivc kovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2050"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.152"},{"key":"e_1_3_2_1_41_1","volume-title":"Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs. arXiv preprint arXiv:2210.10375","author":"Xing Bowen","year":"2022","unstructured":"Bowen Xing and Ivor W Tsang . 2022 a. Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs. arXiv preprint arXiv:2210.10375 (2022). Bowen Xing and Ivor W Tsang. 2022a. Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs. arXiv preprint arXiv:2210.10375 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling. arXiv preprint arXiv:2210.10369","author":"Xing Bowen","year":"2022","unstructured":"Bowen Xing and Ivor W Tsang . 2022b. Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling. arXiv preprint arXiv:2210.10369 ( 2022 ). Bowen Xing and Ivor W Tsang. 2022b. Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling. arXiv preprint arXiv:2210.10369 (2022)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707709"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/567"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1519"},{"key":"e_1_3_2_1_47_1","unstructured":"Xiaodong Zhang and Houfeng Wang. 2016. A joint model of intent determination and slot filling for spoken language understanding. In IJCAI. 2993--2999.  Xiaodong Zhang and Houfeng Wang. 2016. A joint model of intent determination and slot filling for spoken language understanding. In IJCAI. 2993--2999."}],"event":{"name":"CIKM '23: The 32nd ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Birmingham United Kingdom","acronym":"CIKM '23"},"container-title":["Proceedings of the 32nd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3615093","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583780.3615093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:56Z","timestamp":1750178216000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3615093"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,21]]},"references-count":47,"alternative-id":["10.1145\/3583780.3615093","10.1145\/3583780"],"URL":"https:\/\/doi.org\/10.1145\/3583780.3615093","relation":{},"subject":[],"published":{"date-parts":[[2023,10,21]]},"assertion":[{"value":"2023-10-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}