采用面向状态更新操作的方法追求高效地完成状态跟踪,尽可能地减少对不变槽位的重复计算,进而减少任务型对话系统的响应速度。比如,SOM-DST(Selectively Overwriting Memory for Dialogue State Tracking)模型[14]通过减少冗余计算和并行跟踪所有槽位,可以将每轮对话的状态跟踪推理时间缩减为TRADE模型的 8%。
[1] Henderson M, Thomson B, Williams JD. The second dialog state tracking challenge[C]//Proceedings of the 15th annual meeting of the special interest group on discourse and dialogue (SIGDIAL) 2014 Jun (pp. 263-272).
[2] Wen TH, Vandyke D, Mrkšić N, et al. A Network-based End-to-End Trainable Task-oriented Dialogue System[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers 2017 Apr (pp. 438-449).
[3] Budzianowski P, Wen TH, Tseng BH, et al. MultiWOZ-A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing 2018 (pp. 5016-5026).
[4] Zhu Q, Huang K, Zhang Z, et al. CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset[J]. Transactions of the Association for Computational Linguistics. 2020;8:281-95.
[5] Henderson M, Thomson B, Young S. Deep neural network approach for the dialog state tracking challenge[C]//Proceedings of the SIGDIAL 2013 Conference 2013 Aug (pp. 467-471).
[6] Mrkšić N, Séaghdha DÓ, Thomson B, et al. Multi-domain Dialog State Tracking using Recurrent Neural Networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) 2015 Jul (pp. 794-799).
[7] Mrkšić N, Séaghdha DÓ, Wen TH, et al. Neural Belief Tracker: Data-Driven Dialogue State Tracking[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 2017 Jul (pp. 1777-1788).
[8] Wu CS, Madotto A, Hosseini-Asl E, et al. Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics 2019 Jul (pp. 808-819).
[9] Shan Y, Li Z, Zhang J, et al. A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 2020 Jul (pp. 6322-6333).
[10] Zhu S, Li J, Chen L, et al. Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings 2020 Nov (pp. 766-781).
[11] Chen L, Lv B, Wang C, et al. Schema-guided multi-domain dialogue state tracking with graph attention neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence 2020 Apr 3 (Vol. 34, No. 05, pp. 7521-7528).
[12] Hu J, Yang Y, Chen C, et al. SAS: Dialogue state tracking via slot attention and slot information sharing[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 2020 Jul (pp. 6366-6375).
[13] Ye F, Manotumruksa J, Zhang Q, et al. Slot Self-Attentive Dialogue State Tracking[J]. arXiv preprint arXiv:2101.09374. 2021 Jan 22.
[14] Kim S, Yang S, Kim G, et al. Efficient Dialogue State Tracking by Selectively Overwriting Memory[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 2020 Jul (pp. 567-582).
[15] Lin Z, Madotto A, Winata GI, et al. MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020 Nov (pp. 3391-3405).
[16] Gao S, Sethi A, Agarwal S, et al. Dialog State Tracking: A Neural Reading Comprehension Approach[C]//20th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2019 Sep 11 (p. 264)