簡易檢索 / 詳目顯示

回結果列表
研究生： 范植昇
Fan, Jhih-Sheng
論文名稱： 基於事件驅動任務導向進行商家推薦的聊天機器人服務
Chatbot Application: Event driven Task-Oriented Store Recommendation
指導教授： 盧文祥
Lu, Wen-Hsiang
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2017
畢業學年度： 105
語文別： 英文
論文頁數： 55
中文關鍵詞： 事件擷取 、任務預測 、商品探索 、商家推薦
外文關鍵詞： Event Extraction, Task Prediction, Product Discovery, Store Recommendation
相關次數： 點閱：101  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 近年來，隨著mobile服務逐漸的增長，用戶越來越依賴apps來協助完成生活上的各種事物。其中社交類的apps成長最快，而在2016年Facebook提供Facebook Messenger的API接口，讓許多用戶們可以自訂個人的chatbot服務至該平台與其他用戶互動。然而，大部分的chatbot都是屬於domain-specific類型，這樣對於一個用戶要完成一項生活事件是不方便的。 例如：當用戶要過新年時，須分別與Food Bot訂購餐點或餐廳，以及 Clothes Bot 購買新衣，也可能要向Bank Bot取錢。為了要完成一項生活事件，這樣的互動過程浪費很多時間且是繁瑣的。
    為了解決上述所提及問題，我們提出三個階段的框架Event-Task-based Store Recommendation (ETSR)。首先，利用word embedding和word collocation等技術來預測該事件所需進行的相關任務。接著，使用中文廣義知網(E-hownet)分析每項任務的消費傾向，並根據消費傾向來探索合適的商品。最後，收集商家資訊並配合我們提出的三項準則（事件相關性、任務涵蓋度、商品一致性）來推薦合適的商家。

    Recently, with the quick expansion of the mobile service, most users rely on mobile apps to help themselves. The most prominent type of apps is messaging and social. And Facebook launched the Messenger Platform with chatbots and provided the transport information APIs in 2016. The phenomenon reflects the trend which chatbots are growing on many platforms and generating more opportunities for each service in future. However, most chatbots are domain-specific and inconvenient for users to accomplish a life event. Since the services provided by chatbots are diverse, the user must interact with different chatbots to accomplish the needs of a life event, which results in wasting a lot of time and annoying operations.
    To deal with the challenge, we proposed a three-stage framework named Event-Task-based Store Recommendation (ETSR). First part, we predict candidate-tasks which are related to an event based on training word embedding and extract word collocation from users’ diaries. Second part, we analyze consumption tendency of tasks and discover proper products for each task group via a Chinese Knowledge Base. Last part, we design three criteria, which are relevance of an event, coverage of tasks and harmonization of products, to recommend suitable stores.

    摘要 III Abstract IV 致謝 VI Table of Contents VII List of Tables IX List of Figures X Chapter 1 Introduction 1 1.1 Background 1 1.2 Motivation 3 1.3 Methodology 4 1.4 Organization of this Dissertation 5 Chapter 2 Related Research 6 2.1 Event Extraction 6 2.2 Task Prediction 7 2.3 Products and Stores Recommendation 9 Chapter 3 Method 10 3.1 System Architecture 10 3.2 Task Prediction 12 3.2.1 Data Collection and Text Preprocessing 13 3.2.2 Word Embedding Training 13 3.2.3 Task Verb-Object Extraction 15 3.2.4 Task-Object Selection 18 3.2.5 Task-Verb Matching 19 3.2.6 Task Ranking 20 3.3 Product Discovery 21 3.3.1 Consumption Feature Extraction 21 3.3.2 Consumption Tendency Identification and Task-Tendency Grouping 25 3.3.3 Product Matching 26 3.4 Stores Recommendation 26 Chapter 4 Experiments 29 4.1 Experiment Setup 29 4.1.1 Dataset 29 4.1.2 Evaluation Metrics 31 4.2 Performance of Task Prediction 32 4.2.1 Experiment Setup 32 4.2.2 Experiment Result 33 4.3 Performance of Product Discovery 37 4.3.1 Experiment Setup 37 4.3.2 Experiment Result 37 4.4 Performance of Store Recommendation 41 4.4.1 Experiment Setup 41 4.4.2 Experiment Result 42 Chapter 5 Conclusion 48 Chapter 6 Application 49 6.1 Prototype Chatbot System 49 6.2 Tree Structure representation for Event-Task based Store Recommendation 50 Chapter 7 Acknowledge 51 Reference 51

    [1] Facebook. (2016a). Messenger Platform at F8. Facebook Newsroom. Retrieved from http://newsroom.fb.com/news/2016/04/messenger-platform-at-f8
    [2] Facebook. (2016b). Messenger Platform Guidelines. Facebook for Developers. Online at https://developers.facebook.com/docs/messenger-platform
    [3] Jones, R., & Klinkner, K. L. (2008, October). Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs. In Proceedings of the 17th ACM conference on Information and knowledge management (pp. 699-708). ACM.
    [4] Guo, Q., & Agichtein, E. (2010, July). Ready to buy or just browsing?: detecting web searcher goals from interaction data. In Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval (pp. 130-137). ACM.
    [5] Pustejovsky, J., Ingria, B., Sauri, R., Castano, J., Littman, J., Gaizauskas, R., ... & Mani, I. (2005). The specification language TimeML. The language of time: A reader, 545-557.
    [6] Pustejovsky, J., Knippen, R., Littman, J., & Saurí, R. (2005). Temporal and event information in natural language text. Language resources and evaluation, 39(2), 123-164.
    [7] Pustejovsky, J., Lee, K., Bunt, H., & Romary, L. (2010, May). ISO-TimeML: An International Standard for Semantic Annotation. In LREC (Vol. 10, pp. 394-397).
    [8] Teng, C. Y., & Chen, H. H. (2007). Analyzing Temporal Collocations in Weblogs. In ICWSM.
    [9] Kuo, J. J., & Chen, H. H. (2008). Multidocument summary generation: Using informative and event words. Acm transactions on asian language information processing (talip), 7(1), 3.
    [10] Kumaran, G., & Allan, J. (2004, July). Text classification and named entities for new event detection. In Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval (pp. 297-304). ACM.
    [11] Koontz-Garboden, A., & Levin, B. (2003). The morphological typology of change of state event encoding. Morphology and Linguistic Typology, 21, 185.
    [12] Palmer, M., Hwang, J. D., Brown, S. W., Schuler, K. K., & Lanfranchi, A. (2009, March). Leveraging Lexical Resources for the Detection of Event Relations. In AAAI Spring Symposium: Learning by Reading and Learning to Read (pp. 81-87).
    [13] Cao, K., Li, X., & Grishman, R. (2016). Leveraging Dependency Regularization for Event Extraction. In FLAIRS Conference (pp. 20-25).
    [14] Li, Q., Ji, H., & Huang, L. (2013, August). Joint Event Extraction via Structured Prediction with Global Features. In ACL (1) (pp. 73-82).
    [15] Chen, Y., Xu, L., Liu, K., Zeng, D., & Zhao, J. (2015). Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks. In ACL (1) (pp. 167-176).
    [16] Huang, L., Cassidy, T., Feng, X., Ji, H., Voss, C. R., Han, J., & Sil, A. (2016). Liberal event extraction and event schema induction. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-16).
    [17] Feild, H., & Allan, J. (2013, July). Task-aware query recommendation. In Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval (pp. 83-92). ACM.
    [18] Wang, T. X., Tsai, K. Y., & Lu, W. H. (2014). Identifying Real-Life Complex Task Names with Task-Intrinsic Entities from Microblogs. In ACL (2) (pp. 470-475).
    [19] Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of machine Learning research, 3(Jan), 993-1022.
    [20] Hassan, A., White, R. W., Dumais, S. T., & Wang, Y. M. (2014, February). Struggling or exploring?: disambiguating long search sessions. In Proceedings of the 7th ACM international conference on Web search and data mining (pp. 53-62). ACM. Chambers, N., & Jurafsky, D. (2008, June). Unsupervised Learning of Narrative Event Chains. In ACL (Vol. 94305, pp. 789-797).
    [21] Chambers, N., & Jurafsky, D. (2008, June). Unsupervised Learning of Narrative Event Chains. In ACL (Vol. 94305, pp. 789-797).
    [22] Chambers, N., & Jurafsky, D. (2009, August). Unsupervised learning of narrative schemas and their participants. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2-Volume 2 (pp. 602-610). Association for Computational Linguistics.
    [23] Granroth-Wilding, M., & Clark, S. (2016, February). What Happens Next? Event Prediction Using a Compositional Neural Network Model. In AAAI (pp. 2727-2733).
    [24] Burke, R. (2002). Hybrid recommender systems: Survey and experiments. User modeling and user-adapted interaction, 12(4), 331-370.
    [25] Hu, Y., Koren, Y., & Volinsky, C. (2008, December). Collaborative filtering for implicit feedback datasets. In Data Mining, 2008. ICDM'08. Eighth IEEE International Conference on (pp. 263-272). Ieee.
    [26] Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2000, October). Analysis of recommendation algorithms for e-commerce. In Proceedings of the 2nd ACM conference on Electronic commerce (pp. 158-167). ACM.
    [27] Pazzani, M. J., & Billsus, D. (2007). Content-based recommendation systems. In The adaptive web (pp. 325-341). Springer Berlin Heidelberg.
    [28] Esparza, S. G., O’Mahony, M. P., & Smyth, B. (2011). Effective product recommendation using the real-time web. In Research and Development in Intelligent Systems XXVII (pp. 5-18). Springer London.
    [29] Feng, H., & Qian, X. (2013, October). Recommendation via user's personality and social contextual. In Proceedings of the 22nd ACM international conference on Conference on information & knowledge management (pp. 1521-1524). ACM.
    [30] Chen, W. T., Lin, S. C., Huang, S. L., Chung, Y. S., & Chen, K. J. (2010, August). E-HowNet and automatic construction of a lexical ontology. In Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations (pp. 45-48). Association for Computational Linguistics.
    [31] Hsieh, Y. M., Bai, M. H., Chang, J. S., & Chen, K. J. (2012). Improving pcfg chinese parsing with context-dependent probability reestimation. Proceedings of CLP’12, 216-221.
    [32] Socher, R., Perelygin, A., Wu, J. Y., Chuang, J., Manning, C. D., Ng, A. Y., & Potts, C. (2013, October). Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the conference on empirical methods in natural language processing (EMNLP) (Vol. 1631, p. 1642).
    [33] Bansal, M., Gimpel, K., & Livescu, K. (2014). Tailoring Continuous Word Representations for Dependency Parsing. In ACL (2) (pp. 809-815).
    [34] Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
    [35] Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems (pp. 3111-3119).
    [36] Smith, N. A. (2004). Log-linear models. Cited by, 3.

    無法下載圖示 校內：2022-09-01公開
    校外：不公開
    電子論文尚未授權公開，紙本請查館藏目錄
    QR CODE