(54.236.58.220) 您好!臺灣時間:2021/03/01 00:37
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:許正翰
研究生(外文):Cheng-Han Hsu
論文名稱:基於深度學習及Thingtalk之中文虛擬助理
論文名稱(外文):Chinese Virtual Assistant Based On Deep Learning And Thingtalk
指導教授:陳和麟廖世偉
指導教授(外文):Ho-Lin ChenShi-Wei Liao
口試委員:張智威
口試委員(外文):Zhi-Wei Zhang
口試日期:2019-06-17
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:電機工程學研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2019
畢業學年度:107
語文別:英文
論文頁數:37
中文關鍵詞:虛擬助理隱私保障自然語言
DOI:10.6342/NTU201900926
相關次數:
  • 被引用被引用:0
  • 點閱點閱:142
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
Almond是一個開放原始碼、保障隱私、可編程且具擴展性的虛擬助理。Almond提供了一個自然語言使用者介面,使用者不需要撰寫程式碼、不需要學習複雜的程式知識就可以使用。Almond作為一個整合服務平台,使用者可以透過自然語言,去使用、管理、新增和定義自己的網路服務以及互聯網裝置,例如Google信箱、臉書帳戶,使用者可以透過用說的方式,像是“幫我寄信給指導教授”、“幫我在臉書上貼文”、“當溫度高於25度時,打開我的冷氣”等等方式,來使用這些網路服務以及物聯網裝置。

當前市面上的虛擬助理裝置或服務,幾乎都是由大公司所提供,像是亞馬遜公司的Alexa。使用者若要使用這些服務,就必須把私人的資料,如網路服務的帳號、密碼,家中物聯網裝置的存取權限等資訊,提供給這些虛擬助理提供商。如此一來,使用者的資料勢必得集中在這些大公司的平台上,使用者對於自身資料的掌控度因而下降,甚至是隱私權保障等問題,便無法解決。

Almond提供使用者另外一個選擇:使用者可以把所有個人資料都保存在自己的主機,不需要提供給平台提供商。此外,使用者可以很容易地在Almond新增、定義新的網路服務或事物聯網裝置,無須等待裝置供應商或網路服務公司新增。

Almond虛擬助理可以改變目前世界上由主流大公司掌控使用者資料,並藉此影響世界各地廣大使用者的趨勢,改變由大公司定義,甚至操控使用者、操控資訊的情形。Almond開放原始碼虛擬助理提供了使用者不一樣的選擇,讓用戶掌握自己的資料,拿回屬於自己的權利。

ThingTalk是一個專門設計給Almond的程式語言。它可以用來控制網路服務、物聯網裝置。Almond利用深度學習模型來做自然語言語意分析,將自然語言翻譯成Thingtalk。

深度學習模型的訓練需要巨量的訓練資料,而訓練資料的數量以及品質基本上決定了模型的表現。為了產生足夠的訓練資料,Almond提供了一個稱為Genie的訓練資料產出模組及模型訓練流程。這是能夠順利使用Almond的關鍵因素。

全世界第二多人使用的語言就是中文,未來甚至會超過英文使用者的數量。為了讓廣大的中文使用者可以使用、接觸Almond,享受其服務,我們擴展Genie,讓Genie可以支援中文。如此一來,中文使用者就可以輕鬆地使用Almond,一起享受Almond帶來的革命。
Almond, which is an open source virtual assistant, aims at providing a privacy preserving, extensible and programmable virtual assistant which can help people to access the Internet and IoT (Internet of Things) through natural language. Virtual assistants are changing the way people interact with digital world and devices by giving us a uniform programming language, personalized combination of devices and web services, linguistic user interface to our diverse web service, our data, our IoT devices.

Users have the right to decide where they want to put their personal data, when their data can be used, who have access toward their data, and whether they want their personal data to be deleted or not. This is a basic human right that everyone is born to have, and it is now formally protected by the legislator, for example, General Data Protection Regularization (GDPR). Almond provides such virtual assistant that can support functions just like Amazon Alexa yet protect users’ privacy at the same time.

To keep users’ data away from storage in the third party, users are able to define their device and web service in Almond without learning complex programming language. It should be easy to extend new devices and web services by any one. Almond provides such platform to support technical innovations.

Virtual assistant is a game-changer. Today’s big brother companies owning massive volume of private data can exert overwhelming influence on a large population. Almond provide a simple, natural language accessible interface, help users have a better choice of vendors, also have the option to keep their data on their end.

Thingtalk - a virtual assistant programming language - is designed for controlling web service and IoT device on Almond. In order to provide a natural language interface, we need a semantic parser to parse natural language into Thingtalk. Almond utilizes deep learning model to translate natural language into Thingtalk. If we want the model to work, perform extraordinary and achieve our target performance, thousands of data are required for training. To generate this amount of data, Almond provides a generating process called Genie, a generator of training data for the semantic parser in Almond.

Based on this, we extended Genie to support Chinese, so that users who speak Chinese can also benefit from Almond.
誌謝 i
中文摘要 iii
ABSTRACT v
CONTENTS vii
LIST OF FIGURES ix
LIST OF TABLES x
Chapter 1 Introduction 1
1.1 Almond 2
1.1.1 Privacy 3
1.1.2 Extensibility 4
1.1.3 Programmability 4
1.2 Thingpedia 4
1.3 Thingtalk 5
1.4 Genie 8
1.5 Contribution 9
Chapter 2 Related Work 10
2.1 Virtual Assistant 10
2.2 Web service, IoT device 11
2.3 Semantic Parsing 12
Chapter 3 Chinese Compatible Genie 13
3.1 Template Language 13
3.1.1 Primitive templates 14
3.1.2 Construct templates 16
Chapter 4 Semantic Parser 21
4.1 Sequence to sequence 21
4.2 Multiple question answer network 22
4.3 Transformer 25
Chapter 5 Experiments 26
5.1 Evaluation data 26
5.2 Sentences generation 26
5.3 Sequence to sequence model 27
5.4 MQAN 28
5.5 Discussion 29
Chapter 6 Conclusion 31
6.1 Contribution 31
6.2 Future works 31
REFERENCE 32
Giovanni Campagna, Rakesh Ramesh, Silei Xu, Michael Fischer, and Monica S. Lam. 2017. Almond: The Architecture of an Open, Crowdsourced, Privacy-Preserving, Programmable Virtual Assistant. In Proceedings of the 26th International Conference on World Wide Web - WWW ’17. ACM Press, New York, New York, USA, 341–350.

Giovanni Campagna, Silei Xu, Rakesh Ramesh, Michael Fischer, and Monica S. Lam. 2018. Controlling Fine-Grain Sharing in Natural Language with a Virtual Assistant. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2, 3 (sep 2018), 1–28.

Giovanni Campagna, Silei Xu, Mehrad Moradshahi, Richard Socher, and Monica S. Lam. Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands. To appear in Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2019), Phoenix, AZ, June 2019.

I. Beltagy and Chris Quirk. 2016. Improved Semantic Parsers For IfThen Statements. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics.

Douglas MacMillan. 2018. Amazon Says It Has Over 10,000 Employees Working on Alexa, Echo. https://www.wsj.com/articles/amazon-says-it-has-over-10-000-employees-working-on-alexa-echo-1542138284. The Wall Street Journal (2018)

M. Gordon and C. Breazeal. Designing a virtual assistant for in-car child entertainment. In Proceedings of the 14th International Conference on Interaction Design and Children, pages 359–362. ACM, 2015.

P. H. Harvey, E. Currie, P. Daryanani, and J. C. Augusto. Enhancing student support with a virtual assistant. In International Conference on E-Learning, E-Education, and Online Training, pages 101–109. Springer, 2015.

P. Kenny, T. Parsons, J. Gratch, and A. Rizzo. Virtual humans for assisted health care. In Proceedings of the 1st international conference on PErvasive Technologies Related to Assistive Environments, page 6. ACM, 2008.

Marcel van Os, Harry J. Saddler, Lia T. Napolitano, Jonathan H. RUSSELL, Patrick M. LISTER, Rohit DASARI, (2017), United States Patent No. US9338493B2, Retrieved from https://patents.google.com/patent/US9338493B2/en

Anuj Kumar Goyal, Angeliki Metallinou, and Spyros Matsoukas. 2018. Fast and Scalable Expansion of Natural Language Understanding Functionality for Intelligent Agents. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers). Association for Computational Linguistics. https://doi.org/10.18653/v1/n18-3018

C. Dixon, R. Mahajan, S. Agarwal, A. Brush, B. Lee, S. Saroiu, and P. Bahl. An operating system for the home. In Presented as part of the 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12), pages 337–352, 2012.

Google Weave. https://developers.google.com/weave

Samsung SmartThings. http://www.smartthings.com.

Apple HomeKit. http://www.apple.com/ios/home.

Xiaomi Smart Music Box. https://www.mi.com/tw/mi-ai-speaker/

Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei, ImageNet Large Scale Visual Recognition Challenge, In International Journal of Computer Vision (IJCV), 2015, pages 211-252.

Thingpeida, https://almond.stanford.edu/thingpedia

Bryan McCann, Nitish Shirish Keskar, Caiming Xiong, and Richard Socher. 2018. The Natural Language Decathlon: Multitask Learning as Question Answering. arXiv preprint arXiv:1806.08730 (2018).

Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. 3104–3112.

A. Krizhevsky, I. Sutskever, and G. E. Hinton. ImageNet classification with deep convolutional neural networks. In NIPS, 2012.

Q.V. Le, M.A. Ranzato, R. Monga, M. Devin, K. Chen, G.S. Corrado, J. Dean, and A.Y. Ng. Building high-level features using large scale unsupervised learning. In ICML, 2012.

G. Hinton, L. Deng, D. Yu, G. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, and B. Kingsbury. Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Processing Magazine, 2012.

S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural Computation, 1997

Robin Jia and Percy Liang. 2016. Data Recombination for Neural Semantic Parsing. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics. https://doi.org/10.18653/v1/p16-1002

Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. Attention is all you need. In NIPS, 2017.

S. Wang and J. Jiang. Machine comprehension using Match-LSTM and answer pointer. In ICLR, 2017.

M. Seo, A. Kembhavi, A. Farhadi, and H. Hajishirzi. Bidirectional attention flow for machine comprehension. ICLR, 2017.

Xiong, V. Zhong, and R. Socher. Dynamic coattention networks for question answering. ICLR, 2017.

Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov, Enriching Word Vectors with Subword Information, arXiv preprint arXiv:1607.04606. 2017

Armand Joulin, Edouard Grave, Piotr Bojanowski, Tomas Mikolov, Bag of Tricks for Efficient Text Classification, arXiv preprint arXiv:1607.01759. 2017

Martin Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu and Xiaoqiang Zheng, TensorFlow: A system for large-scale machine learning, In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), 2016. https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf

Ashish Vaswani, Samy Bengio, Eugene Brevdo, Francois Chollet, Aidan N. Gomez, Stephan Gouws, Llion Jones, Łukasz Kaiser, Nal Kalchbrenner, Niki Parmar, Ryan Sepassi, Noam Shazeer, Jakob Uszkoreit, Tensor2Tensor for Neural Machine Translation, arXiv preprint arXiv: 1803.07416.

Christopher Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, and David McClosky. 2014. The Stanford CoreNLP Natural Language Processing Toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations. Association for Computational Linguistics. https://doi.org/10.3115/v1/p14-5010

Nitish Srivastava, Geoffrey E Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 15, 1 (2014), 1929–1958.

Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

K. Papineni, S. Roukos, T. Ward, W. J. Zhu, BLEU: a method for automatic evaluation of machine translation, 40th Annual meeting of the Association for Computational Linguistics. pp. 311–318. ACL-2002.

A. Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer, Automatic differentiation in PyTorch, NIPS 2017.

Yushi Wang, Jonathan Berant, and Percy Liang. 2015. Building a Semantic Parser Overnight. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, 1332–1342. https://doi.org/10.3115/v1/p15-1129

Chunyang Xiao, Marc Dymetman, and Claire Gardent. 2016. Sequence based Structured Prediction for Semantic Parsing. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 1341–1350. https://doi.org/10.18653/v1/p16-1127

Xiaojun Xu, Chang Liu, and Dawn Song. 2017. Sqlnet: Generating structured queries from natural language without reinforcement learning. arXiv preprint arXiv:1711.04436 (2017)

Rohit J Kate, Yuk Wah Wong, and Raymond J Mooney. 2005. Learning to transform natural to formal languages. In Proceedings of the 20th national conference on Artificial Intelligence-Volume 3. AAAI Press, 1062–1068.

Yuk Wah Wong and Raymond J. Mooney. 2006. Learning for semantic parsing with statistical machine translation. In Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics. Association for Computational Linguistics, 439–446. https://doi.org/10.3115/1220835.1220891

Victor Zhong, Caiming Xiong, Richard Socher, Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning, arXiv preprint arXiv: 1709.00103 (2017)

Boris A. Trakhtenbrot. 1950. Impossibility of an algorithm for the decision problem in finite classes. Doklady Akademii Nauk SSSR 70 (1950), 569–572. https://doi.org/10.1090/trans2/023/01

Shumo Chu, Chenglong Wang, Konstantin Weitz, and Alvin Cheung. 2017. Cosette: An Automated Prover for SQL. In CIDR.

Internet of Things (IoT) connected devices installed base worldwide from 2015 to 2025 (in billions), https://www.statista.com/statistics/471264/iot-number-of-connected-devices-worldwide/

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., & Polosukhin, I. (2017). Attention Is All You Need. NIPS.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文
 
無相關期刊
 
無相關點閱論文
 
系統版面圖檔 系統版面圖檔