請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68527
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳縕儂(Yun-Nung Chen) | |
dc.contributor.author | Tzu-teng Weng | en |
dc.contributor.author | 翁子騰 | zh_TW |
dc.date.accessioned | 2021-06-17T02:24:07Z | - |
dc.date.available | 2020-08-25 | |
dc.date.copyright | 2020-08-25 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020-08-18 | |
dc.identifier.citation | [1] A. Rastogi, X. Zang, S. Sunkara, R. Gupta, and P. Khaitan, “Towards scalable multidomain conversational agents: The schema-guided dialogue dataset,” arXiv preprint arXiv:1909.05855, 2019. [2] S. Young, M. Gašić, B. Thomson, and J. D. Williams, “Pomdp-based statistical spoken dialog systems: A review,” Proceedings of the IEEE, vol. 101, pp. 1160–1179, May 2013. [3] M. Henderson, B. Thomson, and J. D. Williams, “The second dialog state tracking challenge,” in Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), (Philadelphia, PA, U.S.A.), pp. 263–272, Association for Computational Linguistics, June 2014. [4] N. Mrkšić, D. Ó Séaghdha, T.-H. Wen, B. Thomson, and S. Young, “Neural belief tracker: Data-driven dialogue state tracking,” in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), (Vancouver, Canada), pp. 1777–1788, Association for Computational Linguistics, July 2017. [5] V. Zhong, C. Xiong, and R. Socher, “Global-locally self-attentive encoder for dialogue state tracking,” in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), (Melbourne, Australia), pp. 1458–1467, Association for Computational Linguistics, July 2018. [6] C. G. S. L. A. A. B. P. H. S. J. G. J. L. M. A. M. H. L. L. J. K. K. W. S. L. C. H. A. C. T. K. M. A. R. X. Z. S. S. R. G. Seokhwan Kim, Michel Galley, “The eighth dialog system technology challenge,” arXiv preprint, 2019. [7] C.-S. Wu, A. Madotto, E. Hosseini-Asl, C. Xiong, R. Socher, and P. Fung, “Transferable multi-domain state generator for task-oriented dialogue systems,” The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), 2019. [8] P. Budzianowski, T.-H. Wen, B.-H. Tseng, I. Casanueva, S. Ultes, O. Ramadan, and M. Gašić, “MultiWOZ - a large-scale multi-domain wizard-of-Oz dataset for taskoriented dialogue modelling,” in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, (Brussels, Belgium), pp. 5016–5026, Association for Computational Linguistics, Oct.-Nov. 2018. [9] M. Eric, R. Goel, S. Paul, A. Sethi, S. Agarwal, S. Gao, and D. Hakkani-Tur, “Multiwoz 2.1: Multi-domain dialogue state corrections and state tracking baselines,” 07 2019. [10] J. F. Kelley, “An iterative design methodology for user-friendly natural language office information applications,” ACM Trans. Inf. Syst., vol. 2, p. 26–41, Jan. 1984. [11] J. L. Elman, “Finding structure in time,” Cognitive science, vol. 14, no. 2, pp. 179–211, 1990. [12] Y. Bengio, P. Simard, and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE Transactions on Neural Networks, vol. 5, no. 2, pp. 157–166, 1994. [13] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. [14] K. Cho, B. van Merrienboer, D. Bahdanau, and Y. Bengio, “On the properties of neural machine translation: Encoder-decoder approaches,” CoRR, vol. abs/1409.1259, 2014. [15] J. D. Williams and S. Young, “Partially observable markov decision processes for spoken dialog systems,” Comput. Speech Lang., vol. 21, pp. 393–422, Apr. 2007. [16] B. Thomson and S. Young, “Bayesian update of dialogue state: A pomdp framework for spoken dialogue systems,” Comput. Speech Lang., vol. 24, pp. 562–588, Oct. 2010. [17] Z. Wang and O. Lemon, “A simple and generic belief tracking mechanism for the dialog state tracking challenge: On the believability of observed information,” in SIGDIAL Conference, 2013. [18] J. D. Williams, “Web-style ranking and SLU combination for dialog state tracking,” in Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), (Philadelphia, PA, U.S.A.), pp. 282–291, Association for Computational Linguistics, June 2014. [19] L. Zilka and F. Jurcícek, “Incremental lstm-based dialog state tracker,” 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 757–762, 2015. [20] N. Mrkšić, D. Ó Séaghdha, B. Thomson, M. Gašić, P.-H. Su, D. Vandyke, T.-H. Wen, and S. Young, “Multi-domain dialog state tracking using recurrent neural networks,” in 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), (Beijing, China), pp. 794–799, Association for Computational Linguistics, July 2015. [21] H. Lee, J. Lee, and T.-Y. Kim, “Sumbt: Slot-utterance matching for universal and scalable belief tracking,” in Proceedings of the 57th Conference of the Association for Computational Linguistics, pp. 5478–5483, 2019. [22] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018. [23] G. Chao and I. Lane, “BERT-DST: scalable end-to-end dialogue state tracking with bidirectional encoder representations from transformer,” CoRR, vol. abs/1907.03040, 2019. [24] J. Pennington, R. Socher, and C. D. Manning, “Glove: Global vectors for word representation,” in Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543, 2014. [25] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68527 | - |
dc.description.abstract | 領域獨立的對話狀態追蹤近期在任務導向對話系統的研究當中非常熱門。本篇論文嘗試提出了一個輕量化的模型LION-Net來處理零樣本對話狀態追蹤問題。LION-Net有使用到seq2seq模型,與copy和attention機制。我們的模型利用了服務,意圖和插槽的自然語言敘述作為輸入,並且能在不同對話領域中分享參數,使得我們的模型可以在未見過的對話領域做零樣本預測。本篇論文實驗所使用的資料集是最新釋出的Schema-guided dialogue dataset(以下簡稱SGD)。實驗結果顯示我們提出的模型在效能上大部分優於Google所提出的基線模型,而且其記憶體使用量較少和訓練時間較短。 我們也針對架構引導方法進行了驗證,而我們發現此方法有效,但是有些限制。 | zh_TW |
dc.description.abstract | Domain-independent dialogue state tracking has received much attention in the recent studies of task-oriented dialogue systems. In this paper, we propose a LIghtweight ONtology-independent (LION) sequence-to-sequence model with copy and attention mechanisms to tackle the zero-shot dialogue state tracking problem. By sharing the parameters across domains and using the natural language descriptions of the services, intents, and slots as the input, our model enables zero-shot generalization to an unseen domain.The experiments are conducted on the newly-released schema-guided dialogue dataset, and our model outperforms the Google baseline on most metrics while requiring considerably less computational cost, both in memory usage and training time. We also validated the schema-guided approach and we found that the schema-guided approach is effective but has some limitations. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T02:24:07Z (GMT). No. of bitstreams: 1 U0001-1708202012330800.pdf: 1302427 bytes, checksum: 31b358d174ab8776dc98c099be053a79 (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 誌謝 iii Acknowledgements v 摘要 vii Abstract ix 1 Introduction 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Task Description . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.3 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.4 Main Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.5 Thesis Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2 Background 7 2.1 Recurrent Neural Models . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.1.1 Recurrent Neural Network (RNN) . . . . . . . . . . . . . . . . . 7 2.1.2 Gated Recurrent Unit (GRU) . . . . . . . . . . . . . . . . . . . 8 2.2 Sequence-to-Sequence Learning . . . . . . . . . . . . . . . . . . 8 3 Related Work 11 3.1 Dialogue state tracking . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.2 TRADE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.3 BERT baseline by Google . . . . . . . . . . . . . . . . . . . . 13 4 Model Architecture 15 4.1 Utterance Encoder . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.2 Schema Embedding . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4.2.1 Active Intent . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.2.2 Requested Slots . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.3 Slot Value Decoder . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.3.1 Slot Prediction . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.4 Training . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.5 Experiments . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 4.5.1 Settings . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 4.6 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 5 Validation of the schema-guided approach 27 5.1 Experiment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 5.1.1 Experimental Settings . . . . . . . . . . . . . . . . . . . . . . . 28 5.1.2 Results and discussion . . . . . . . . . . . . . . . . . . . . . . . 28 5.2 Investigating the causes of performance drop . . . . . . . . . . . . . . . 30 5.2.1 Results and Discussion . . . . . . . . . . . . . . . . . . . . . . . 31 6 Conclusion and Future Work 41 Bibliography 43 | |
dc.language.iso | en | |
dc.title | 輕量化架構導向對話狀態追蹤模型以及其泛化能力之驗證 | zh_TW |
dc.title | Lightweight Schema-Guided Dialogue State Tracker and Validation of Generalizability | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 李宏毅(Hung-yi Lee),曹昱(Yu Tsao) | |
dc.subject.keyword | 對話狀態追蹤,任務導向型對話系統,架構引導方法, | zh_TW |
dc.subject.keyword | Dialogue state tracking,task-oriented dialogue system,schema-guided approach, | en |
dc.relation.page | 46 | |
dc.identifier.doi | 10.6342/NTU202003720 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2020-08-19 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-1708202012330800.pdf 目前未授權公開取用 | 1.27 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。