{"type":"ScholarlyArticle","title":"Decoupling Breaks Data Barriers: A Decoupled Pre-training Framework for Multi-intent Spoken Language Understanding","authors":[{"name":"Libo Qin","slug":"libo-qin","given":"Libo","family":"Qin","affiliation":"School of Computer Science and Engineering , Central South University , China"},{"name":"Qiguang Chen","slug":"qiguang-chen","given":"Qiguang","family":"Chen","affiliation":"Research Center for Social Computing and Information Retrieval; Harbin Institute of Technology , China"},{"name":"Jingxuan Zhou","slug":"jingxuan-zhou","given":"Jingxuan","family":"Zhou","affiliation":"School of Computer Science and Engineering , Central South University , China"},{"name":"Qinzheng Li","slug":"qinzheng-li","given":"Qinzheng","family":"Li","affiliation":"School of Computer Science and Engineering , Central South University , China"},{"name":"Chunlin Lu","slug":"chunlin-lu","given":"Chunlin","family":"Lu","affiliation":"School of Computer Science and Engineering , Central South University , China"},{"name":"Wanxiang Che","slug":"wanxiang-che","given":"Wanxiang","family":"Che","affiliation":"Research Center for Social Computing and Information Retrieval; Harbin Institute of Technology , China"}],"abstract":"Multi-intent Spoken Language Understanding (Multi-intent SLU) can extract multiple intents in a single utterance, gaining increasing attention. Nevertheless, current multi-intent SLU approaches still heavily rely on large amounts of annotated multi-intent SLU data, which makes it hard to be satisfied in real-world scenarios without sufficient data. Motivated by this, we introduce a novel decoupled pre-training framework (DPF) to address the data-scarcity problem, achieving to leverage of abundant multi-intent-free SLU data to enhance multi-intent SLU. Specifically, DPF first decouples the multi-intent SLU task into two abilities: (1) task-agnostic ability to locate the task-agnostic slot entity span and (2) task-specific ability to predict the task-specific slot and intent labels simultaneously. The key insight of DPF is that such decomposition allows us to design a two-stage decoupled pre-training procedure to enhance both task-agnostic ability and task-specific ability with abundant multi-intent-free SLU data (i.e., NER and single-intent SLU data), respectively. Experimental results on two standard benchmarks (e.g., MixATIS and MixSNIPS) demonstrate the effectiveness of DPF by achieving superior performance. In addition, extensive analyses reveal that utilizing the multi-intent-free data can effectively enhance multi-intent SLU.","doi":"10.24963/ijcai.2024/715","url":"https://ijcai.org/proceedings/2024/715","pdf":"https://ijcai.org/proceedings/2024/0715.pdf","markdown":"https://ijcai.org/proceedings/2024/715.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/715","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Natural Language Processing","track":"Main Track","number":715,"pages":{"first":6469,"last":6477},"keywords":["Natural Language Processing: NLP: Dialogue and interactive systems"],"videos":[],"references":[{"position":1,"raw":"[Al-Rfou et al., 2015] Rami Al-Rfou, Vivek Kulkarni, Bryan Perozzi, and Steven Skiena. Polyglot-NER: Massive mul- tilingual named entity recognition. Proc. of ICDM89, 2015.","title":"Polyglot-NER: Massive multilingual named entity recognition","authors":"Rami Al-Rfou, Vivek Kulkarni, Bryan Perozzi, Steven Skiena","year":"2015","venue":"Proc. of ICDM89","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bastianelli et al., 2020] Emanuele Bastianelli, Andrea Vanzo, Pawel Swietojanski, and Verena Rieser. SLURP: A spoken language understanding resource package. In Proc. of EMNLP, 2020.","title":"SLURP: A spoken language understanding resource package","authors":"Emanuele Bastianelli, Andrea Vanzo, Pawel Swietojanski, Verena Rieser","year":"2020","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2022a] Lisong Chen, Peilin Zhou, and Yuexian Zou. Joint multiple intent detection and slot filling via self- distillation. In Proc. of ICASSP, 2022.","title":"Joint multiple intent detection and slot filling via selfdistillation","authors":"Chen","year":"2022","venue":"Proc. of ICASSP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2022b] Lisung Chen, Nuo Chen, Yuexian Zou, Yong Wang, and Xinzhong Sun. A transformer-based threshold-free framework for multi-intent NLU. In Proc. of COLING, 2022.","title":"A transformer-based threshold-free framework for multi-intent NLU","authors":"Chen","year":"2022","venue":"Proc. of COLING","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cheng et al., 2023a] Xuxin Cheng, Zhihong Zhu, Bowen Cao, Qichen Ye, and Yuexian Zou. MRRL: Modify- ing the reference via reinforcement learning for non- autoregressive joint multiple intent detection and slot fill- ing. In Proc. of EMNLP Findings, 2023.","title":"MRRL: Modifying the reference via reinforcement learning for nonautoregressive joint multiple intent detection and slot filling","authors":"Cheng","year":"2023","venue":"Proc. of EMNLP Findings","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cheng et al., 2023b] Xuxin Cheng, Zhihong Zhu, Wanshi Xu, Yaowei Li, Hongxiang Li, and Yuexian Zou. Ac- celerating multiple intent detection and slot filling via tar- geted knowledge distillation. In Proc. of EMNLP Find- ings, 2023.","title":"Accelerating multiple intent detection and slot filling via targeted knowledge distillation","authors":"Cheng","year":"2023","venue":"Proc. of EMNLP Findings","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Coucke et al., 2018] Alice Coucke, Alaa Saade, Adrien Ball, Théodore Bluche, Alexandre Caulier, David Leroy, Clément Doumouro, Thibault Gisselbrecht, Francesco Caltagirone, Thibaut Lavril, et al. Snips voice plat- form: an embedded spoken language understanding sys- tem for private-by-design voice interfaces. arXiv preprint arXiv:1805.10190, 2018.","title":"Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces","authors":"Alice Coucke, Alaa Saade, Adrien Ball, Théodore Bluche, Alexandre Caulier, David Leroy, Clément Doumouro, Thibault Gisselbrecht, Francesco Caltagirone, Thibaut Lavril","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Derczynski et al., 2017] Leon Derczynski, Eric Nichols, Marieke van Erp, and Nut Limsopatham. Results of the WNUT2017 shared task on novel and emerging entity recognition. In Proc. of WNUT, 2017. Fetahu et al., 2021]","title":"Results of the WNUT2017 shared task on novel and emerging entity recognition","authors":"Leon Derczynski, Eric Nichols, Marieke Van Erp, Nut Limsopatham","year":"2017","venue":"Proc. of WNUT","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"Besnik Fetahu, Anjie Fang, Oleg Rokhlenko, and Shervin Malmasi. Gazetteer enhanced named entity recognition for code-mixed web queries. In Proc. of SIGIR, 2021.","title":"Gazetteer enhanced named entity recognition for code-mixed web queries","authors":"Besnik Fetahu, Anjie Fang, Oleg Rokhlenko, Shervin Malmasi","year":"2021","venue":"Proc. of SIGIR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[FitzGerald et al., 2023] Jack FitzGerald, Christopher Hench, Charith Peris, Scott Mackie, Kay Rottmann, Ana Sanchez, Aaron Nash, Liam Urbach, Vishesh Kakarala, Richa Singh, Swetha Ranganath, Laurie Crist, Misha Bri- tan, Wouter Leeuwis, Gokhan Tur, and Prem Natarajan. MASSIVE: A 1M-example multilingual natural language understanding dataset with 51 typologically-diverse languages. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Proc. of the ACL, 2023.","title":"MASSIVE: A 1M-example multilingual natural language understanding dataset with 51 typologically-diverse languages","authors":"Fitzgerald","year":"2023","venue":"Proc. of the ACL","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gangadharaiah and Narayanaswamy, 2019] Rashmi Gan- gadharaiah and Balakrishnan Narayanaswamy. Joint multiple intent detection and slot labeling for goal- oriented dialog. In Proc. of NAACL, 2019.","title":"Joint multiple intent detection and slot labeling for goaloriented dialog","authors":"Rashmi Gangadharaiah, Balakrishnan Narayanaswamy","year":"2019","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Goo et al., 2018] Chih-Wen Goo, Guang Gao, Yun-Kai Hsu, Chih-Li Huo, Tsung-Chieh Chen, Keng-Wei Hsu, and Yun-Nung Chen. Slot-gated modeling for joint slot filling and intent prediction. In Proc. of NAACL, 2018.","title":"Slot-gated modeling for joint slot filling and intent prediction","authors":"Chih-Wen Goo, Guang Gao, Yun-Kai Hsu, Chih-Li Huo, Tsung-Chieh Chen, Keng-Wei Hsu, Yun-Nung Chen","year":"2018","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Gururangan et al., 2020] Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Belt- agy, Doug Downey, and Noah A. Smith. Don't stop pretraining: Adapt language models to domains and tasks. In Proc. of ACL, 2020.","title":"Don't stop pretraining: Adapt language models to domains and tasks","authors":"Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, Noah A Smith","year":"2020","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[He et al., 2023] Pengcheng He, Jianfeng Gao, and Weizhu Chen. DeBERTav3: Improving deBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing. In Proc. of ICLR, 2023.","title":"DeBERTav3: Improving deBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing","authors":"Pengcheng He, Jianfeng Gao, Weizhu Chen","year":"2023","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Hemphill et al., 1990] Charles T. Hemphill, John J. God- frey, and George R. Doddington. The ATIS spoken lan- guage systems pilot corpus. In Speech and Natural Lan- guage: Proceedings of a Workshop Held at Hidden Valley, Pennsylvania, June 24-27,1990, 1990.","title":"The ATIS spoken language systems pilot corpus","authors":"Charles T Hemphill, John J Godfrey, George R Doddington","year":"1990","venue":"Speech and Natural Language: Proceedings of a Workshop Held at Hidden","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liang et al., 2020] Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Lin- jun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Daniel Campos, Rangan Ma- jumder, and Ming Zhou. XGLUE: A new benchmark dataset for cross-lingual pre-training, understanding and generation. In Proc. of EMNLP, 2020.","title":"XGLUE: A new benchmark dataset for cross-lingual pre-training, understanding and generation","authors":"Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Daniel Campos, Rangan Majumder, Ming Zhou","year":"2020","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ling and Weld, 2012] Xiao Ling and Daniel Weld. Fine- grained entity recognition. In Proc. of AAAI, 2012.","title":"Finegrained entity recognition","authors":"Xiao Ling, Daniel Weld","year":"2012","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2013] Jingjing Liu, Panupong Pasupat, Scott Cyphers, and Jim Glass. Asgard: A portable architecture for multilingual dialogue systems. In Proc. of ICASSP, 2013.","title":"Asgard: A portable architecture for multilingual dialogue systems","authors":"Jingjing Liu, Panupong Pasupat, Scott Cyphers, Jim Glass","year":"2013","venue":"Proc. of ICASSP","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Liu et al., 2021] Xingkun Liu, Arash Eshghi, Pawel Swi- etojanski, and Verena Rieser. Benchmarking Natural Language Understanding Services for Building Conversa- tional Agents. 2021.","title":"Benchmarking Natural Language Understanding Services for Building Conversational Agents","authors":"Liu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Loshchilov and Hutter, 2019] Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization. In Proc. of ICLR, 2019.","title":"Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization","authors":"Hutter Loshchilov","year":"2019","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Pan et al., 2017] Xiaoman Pan, Boliang Zhang, Jonathan May, Joel Nothman, Kevin Knight, and Heng Ji. Cross- lingual name tagging and linking for 282 languages. In Proc. of ACL, 2017.","title":"Crosslingual name tagging and linking for 282 languages","authors":"Pan","year":"2017","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Pan et al., 2023] Wenbo Pan, Qiguang Chen, Xiao Xu, Wanxiang Che, and Libo Qin. A preliminary evaluation of chatgpt for zero-shot dialogue understanding. arXiv preprint arXiv:2304.04256, 2023.","title":"A preliminary evaluation of chatgpt for zero-shot dialogue understanding","authors":"Wenbo Pan, Qiguang Chen, Xiao Xu, Wanxiang Che, Libo Qin","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Pham et al., 2023] Thinh Pham, Chi Tran, and Dat Quoc Nguyen. MISCA: A joint model for multiple intent detec- tion and slot filling with intent-slot co-attention. In Proc. of EMNLP Findings, 2023.","title":"MISCA: A joint model for multiple intent detection and slot filling with intent-slot co-attention","authors":"Thinh Pham, Chi Tran, Dat Quoc Nguyen","year":"2023","venue":"Proc. of EMNLP Findings","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Pradhan et al., 2013] Sameer Pradhan, Alessandro Mos- chitti, Nianwen Xue, Hwee Tou Ng, Anders Björkelund, Olga Uryupina, Yuchen Zhang, and Zhi Zhong. Towards robust linguistic analysis using OntoNotes. In Proc. of CoNLL, 2013.","title":"Towards robust linguistic analysis using OntoNotes","authors":"Alessandro Sameer Pradhan, Nianwen Moschitti, Xue, Tou Hwee, Anders Ng, Olga Björkelund, Yuchen Uryupina, Zhi Zhang, Zhong","year":"2013","venue":"Proc. of CoNLL","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Qin et al., 2019] Libo Qin, Wanxiang Che, Yangming Li, Haoyang Wen, and Ting Liu. A stack-propagation frame- work with token-level intent detection for spoken language understanding. In Proc. of EMNLP, 2019.","title":"A stack-propagation framework with token-level intent detection for spoken language understanding","authors":"Libo Qin, Wanxiang Che, Yangming Li, Haoyang Wen, Ting Liu","year":"2019","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Qin et al., 2020] Libo Qin, Xiao Xu, Wanxiang Che, and Ting Liu. AGIF: An adaptive graph-interactive framework for joint multiple intent detection and slot filling. In Proc. of EMNLP Findings, 2020.","title":"AGIF: An adaptive graph-interactive framework for joint multiple intent detection and slot filling","authors":"Libo Qin, Xiao Xu, Wanxiang Che, Ting Liu","year":"2020","venue":"Proc. of EMNLP Findings","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Qin et al., 2021a] Libo Qin, Tailu Liu, Wanxiang Che, Bingbing Kang, Sendong Zhao, and Ting Liu. A co- interactive transformer for joint slot filling and intent de- tection. In Proc. of ICASSP, 2021.","title":"A cointeractive transformer for joint slot filling and intent detection","authors":"Qin","year":"2021","venue":"Proc. of ICASSP","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Qin et al., 2021b] Libo Qin, Fuxuan Wei, Tianbao Xie, Xiao Xu, Wanxiang Che, and Ting Liu. GL-GIN: Fast and accurate non-autoregressive model for joint multiple intent detection and slot filling. In Proc. of ACL, 2021.","title":"GL-GIN: Fast and accurate non-autoregressive model for joint multiple intent detection and slot filling","authors":"Qin","year":"2021","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Qin et al., 2021c] Libo Qin, Tianbao Xie, Wanxiang Che, and Ting Liu. A survey on spoken language understand- ing: Recent advances and new frontiers. In Zhi-Hua Zhou, editor, Proc. of the IJCAI, pages 4577-4584. International Joint Conferences on Artificial Intelligence Organization, 8 2021. Survey Track.","title":"A survey on spoken language understanding: Recent advances and new frontiers","authors":"Qin","year":"2021","venue":"International Joint Conferences on Artificial Intelligence Organization","doi":null,"url":null,"internal_url":"/proceedings/2021/622"},{"position":30,"raw":"[Qin et al., 2023] Libo Qin, Qiguang Chen, Xiao Xu, Yun- long Feng, and Wanxiang Che. OpenSLU: A unified, mod- ularized, and extensible toolkit for spoken language under- standing. In Proc. of ACL Demo, 2023.","title":"OpenSLU: A unified, modularized, and extensible toolkit for spoken language understanding","authors":"Libo Qin, Qiguang Chen, Xiao Xu, Yunlong Feng, Wanxiang Che","year":"2023","venue":"Proc. of ACL Demo","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Ritter et al., 2011] Alan Ritter, Sam Clark, Mausam, and Oren Etzioni. Named entity recognition in tweets: An ex- perimental study. In Proc. of EMNLP, 2011.","title":"Named entity recognition in tweets: An experimental study","authors":"Alan Ritter, Sam Clark, Mausam, Oren Etzioni","year":"2011","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Sang and De Meulder, 2003] Erik F Sang and Fien De Meulder. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. In Proc. of AACL, 2003.","title":"Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition","authors":"Sang, De Meulder, ; ] Erik, F Sang, Fien De, Meulder","year":"2003","venue":"Proc. of AACL","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Schuster et al., 2019] Sebastian Schuster, Sonal Gupta, Rushin Shah, and Mike Lewis. Cross-lingual transfer learning for multilingual task oriented dialog. In Proc. of NAACL, 2019.","title":"Cross-lingual transfer learning for multilingual task oriented dialog","authors":"Sebastian Schuster, Sonal Gupta, Rushin Shah, Mike Lewis","year":"2019","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Song et al., 2022a] Feifan Song, Lianzhe Huang, and Houfeng Wang. A unified framework for multi-intent spoken language understanding with prompting. arXiv preprint arXiv:2210.03337, 2022.","title":"A unified framework for multi-intent spoken language understanding with prompting","authors":"Song","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Song et al., 2022b] Mengxiao Song, Bowen Yu, Li Quan- gang, Wang Yubin, Tingwen Liu, and Hongbo Xu. En- hancing joint multiple intent detection and slot filling with global intent-slot co-occurrence. In Proc. of EMNLP, 2022.","title":"Enhancing joint multiple intent detection and slot filling with global intent-slot co-occurrence","authors":"Song","year":"2022","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Sowański and Janicki, 2020] Marcin Sowański and Artur Janicki. Leyzer: A dataset for multilingual virtual assis- tants. In International Conference on Text, Speech, and Dialogue, 2020.","title":"Leyzer: A dataset for multilingual virtual assistants","authors":"Janicki Sowański, Marcin Sowański, Artur Janicki","year":"2020","venue":"International Conference on Text, Speech, and Dialogue","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Tedeschi and Navigli, 2022] Simone Tedeschi and Roberto Navigli. MultiNERD: A multilingual, multi-genre and fine-grained dataset for named entity recognition (and dis- ambiguation). In Proc. of ACL Findings, 2022.","title":"MultiNERD: A multilingual, multi-genre and fine-grained dataset for named entity recognition (and disambiguation)","authors":"Simone Tedeschi, Roberto Navigli","year":"2022","venue":"Proc. of ACL Findings","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Tedeschi et al., 2021] Simone Tedeschi, Valentino Maiorca, Niccolò Campolungo, Francesco Cecconi, and Roberto Navigli. WikiNEuRal: Combined neural and knowledge- based silver data creation for multilingual NER. In Proc. of EMNLP Findings, 2021.","title":"WikiNEuRal: Combined neural and knowledgebased silver data creation for multilingual NER","authors":"Simone Tedeschi, Valentino Maiorca, Niccolò Campolungo, Francesco Cecconi, Roberto Navigli","year":"2021","venue":"Proc. of EMNLP Findings","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Tur and De Mori, 2011] Gokhan Tur and Renato De Mori. Spoken language understanding: Systems for extracting semantic information from speech. John Wiley & Sons, 2011.","title":"Spoken language understanding: Systems for extracting semantic information from speech","authors":"De Tur, ; Mori, Gokhan Tur, Renato De Mori","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[van der Goot et al., 2021] Rob van der Goot, Ibrahim Sharaf, Aizhan Imankulova, Ahmet Üstün, Marija Stepanovic, Alan Ramponi, Siti Oryza Khairunnisa, Mamoru Komachi, and Barbara Plank. From masked- language modeling to translation: Non-English auxiliary tasks improve zero-shot spoken language understanding. In Proc. of NAACL, 2021.","title":"From maskedlanguage modeling to translation: Non-English auxiliary tasks improve zero-shot spoken language understanding","authors":"Goot Van Der","year":"2021","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Wan et al., 2023] Xue Wan, Wensheng Zhang, Mengxing Huang, Siling Feng, and Yuanyuan Wu. A unified ap- proach to nested and non-nested slots for spoken language understanding. Electronics, 2023.","title":"A unified approach to nested and non-nested slots for spoken language understanding","authors":"Xue Wan, Wensheng Zhang, Mengxing Huang, Siling Feng, Yuanyuan Wu","year":"2023","venue":"Electronics","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Weischedel and Brunstein, 2005] Ralph Weischedel and Ada Brunstein. Bbn pronoun coreference and entity type corpus. Linguistic Data Consortium, Philadelphia, 2005.","title":"Bbn pronoun coreference and entity type corpus","authors":"Brunstein Weischedel, Ralph Weischedel, Ada Brunstein","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Wu et al., 2022] Yangjun Wu, Han Wang, Dongxiang Zhang, Gang Chen, and Hao Zhang. Incorporating in- structional prompts into a unified generative framework for joint multiple intent detection and slot filling. In Proc. of COLING, 2022.","title":"Incorporating instructional prompts into a unified generative framework for joint multiple intent detection and slot filling","authors":"Wu","year":"2022","venue":"Proc. of COLING","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Xing and Tsang, 2022] Bowen Xing and Ivor Tsang. Co- guiding net: Achieving mutual guidances between mul- tiple intent detection and slot filling via heterogeneous semantics-label graphs. In Proc. of EMNLP, 2022.","title":"Coguiding net: Achieving mutual guidances between multiple intent detection and slot filling via heterogeneous semantics-label graphs","authors":"Tsang ; ] Xing, Xing Bowen, Ivor Tsang","year":"2022","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Young et al., 2013] Steve Young, Milica Gašić, Blaise Thomson, and Jason D. Williams. Pomdp-based statistical spoken dialog systems: A review. Proc. of IEEE, 2013.","title":"Pomdp-based statistical spoken dialog systems: A review","authors":"Steve Young, Milica Gašić, Blaise Thomson, Jason D Williams","year":"2013","venue":"Proc. of IEEE","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Zeldes, 2017] Amir Zeldes. The GUM corpus: Creating multilayer resources in the classroom. Language Re- sources and Evaluation, 2017.","title":"The GUM corpus: Creating multilayer resources in the classroom","authors":"Amir Zeldes, Zeldes","year":"2017","venue":"Language Resources and Evaluation","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Zhu et al., 2023] Zhihong Zhu, Weiyuan Xu, Xuxin Cheng, Tengtao Song, and Yuexian Zou. A dynamic graph inter- active framework with label-semantic injection for spoken language understanding. In Proc. of ICASSP, 2023.","title":"A dynamic graph interactive framework with label-semantic injection for spoken language understanding","authors":"Zhihong Zhu, Weiyuan Xu, Xuxin Cheng, Tengtao Song, Yuexian Zou","year":"2023","venue":"Proc. of ICASSP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}