現今網路上非常多經濟行為的服務項目都引進了聊天機器人，由於聊天機器人可以不間斷的在線上服務客戶，並且不需要額外的人力來進行問題回答，因此可以減少成本並延長整體服務時間。在與使用者的互動中常常會是機器人給定固定的選項給使用者挑選；又或者是自由輸入問題時未符合機器人配對的格式則不予以回答並引導其他回答，使得使用者體驗可以有進步的空間。
由於宅經濟以及網路上娛樂產業的發達，在網路上的生產消費行為也日益增加。隨著Web2.0的發展，許多消費行為的評論也隨之出現，在電玩產品中，非常多消費者仰賴著網路上的評論來進行消費或者是進行遊戲內容的討論，以獲得更好的遊戲體驗。消費者可能會依靠關鍵字的搜尋來找到相關資訊，但是僅靠關鍵字搜尋有下列的缺點：消費者也可能因為對於遊戲的不熟悉，沒辦法下正確的關鍵字來搜尋，或在下正確的關鍵字之前可能就需花費許多時間在尋找適合的關鍵字，且搜尋結果還要人工過濾並判讀，可能過度的浪費時間在過濾資訊上。若這時讓使用者以自然語言問答，如現在的智慧型助理以及聊天機器人，可加快使用者找到適合的答案。聊天機器人人為可以進行領域性的客製化，相較於智慧型助理屬於非領域性的機器人，處理的目標為生活中的行程安排或者是廣泛的知識搜尋，聊天機器人更適合作為提供電玩遊戲消費者資訊的一個管道。
綜合上述提到聊天機器人目前在與使用者互動上有較為瑣碎的問題或者無法回答，以及非領域性機器人並沒辦法有效的進行領域性問答，本研究將提出一個透過篩選文件的方法以及包含問題資訊的架構的語言知識模型，以深度學習中的卷積神經網路來進行語意的配對，並從非結構化的文件中透過循環神經網路產生出完整答案提供給使用者，藉此讓使用者可以在利用現有資訊的情形之下對聊天機器人進行提問也可以得到完整並且符合使用者提問的答案，本研究的方法和baseline的Pointer-Generator相比之下在ROUGE上約有0.0334的上昇。

In the era of the Internet, many online economic behaviors are using chatbot as their promotion means. Using chatbot to serve these online customers is beneficial when there is no need to hire another employee for responding to customer questions and it is 24/7 available. Although chatbot is useful in many ways, most of the time the customer has to type in questions that match the recognition pattern or choose from the default options to open up a conversation with the chatbot which makes it somewhat inconvenient. With the prosperity of home economy and entertainment industry, video gamers leave comments to forums to discuss how to solve the problems in game to let other gamers could have completely experienced what the game is about. When a newcomer plays the game and a problem or question occurs, he or she could have trouble in finding a solution to the question since he or she doesn’t have enough knowledge to the game. Then the gamer should enrich himself or herself to find the proper keyword to the question or spending time on searching the discussion forum to find the right answer. By using Natural Language Processing (NLP) systems like chatbot, one could get proper information to the question more quickly. Using deep learning techniques and the keyword filtering mechanism and question layer information added, the proposed method has been found to improve about 3.34% in ROUGE compared to pointer-generator network. The answers produced by this study has been evaluated to show that the study can produce a comprehensive and informational answer which helps to assist newcomers to the game quickly find their own needs.

AbuShawar, B., & Atwell, E. (2015). ALICE Chatbot: Trials and Outputs. Computación y Sistemas, 19(4), 625-632.
Allahyari, M., Pouriyeh, S., Assefi, M., Safaei, S., Trippe, E. D., Gutierrez, J. B., & Kochut, K. (2017). Text Summarization Techniques: A Brief Survey. arXiv preprint arXiv:1707.02268.
Berthon, P. R., Pitt, L. F., Plangger, K., & Shapiro, D. (2012). Marketing Meets Web 2.0, Social Media, and Creative Consumers: Implications for International Marketing Strategy. Business horizons, 55(3), 261-271.
Bouziane, A., Bouchiha, D., Doumi, N., & Malki, M. (2015). Question Answering Systems: Survey and Trends. Procedia Computer Science, 73, 366-375.
Cho, K., Merriënboer, B. V., Bahdanau, D., & Bengio, Y. (2014). On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. arXiv preprint arXiv:1409.1259.
Cho, K., Merriënboer, B. V., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation. arXiv preprint arXiv:1406.1078.
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. arXiv preprint arXiv:1412.3555.
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. (2011). Natural Language Processing (Almost) from Scratch. Journal of Machine Learning Research, 12, 2493-2537.
Cox, J., & Kaimann, D. (2015). How Do Reviews from Professional Critics Interact With Other Signals of Product Quality? Evidence from the Video Game Industry. Journal of Consumer Behaviour, 14(6), 366-377.
Cui, L., Huang, S., Wei, F., Tan, C., Duan, C., & Zhou, M. (2017). Superagent: A Customer Service Chatbot for E-commerce Websites. Proceedings of ACL 2017, System Demonstrations, 97-102.
Diefenbach, D., Lopez, V., Singh, K., & Maret, P. (2018). Core Techniques of Question Answering Systems Over Knowledge Bases: a Survey. Knowledge and Information Systems, 55(3), 529-569.
Dwivedi, S. K., & Singh, V. (2013). Research and Reviews in Question Answering System. Procedia Technology, 10, 417-424.
GameFAQs. from https://gamefaqs.gamespot.com/
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., . . . Chen, T. (2018). Recent Advances in Convolutional Neural Networks. Pattern Recognition, 77, 354-377.
Guo, B., & Zhou, S. (2017). What Makes Population Perception of Review Helpfulness: An Information Processing Perspective. Electronic Commerce Research, 17(4), 585-608.
Guo, J., Fan, Y., Ai, Q., & Bruce, C. W. (2016). A Deep Relevance Matching Model for Ad-hoc Retrieval. Paper presented at the Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, Indianapolis, Indiana, USA.
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780.
Hu, B., Lu, Z., Li, H., & Chen, Q. (2014). Convolutional Neural Network Architectures for Matching Natural Language Sentences. Paper presented at the Advances in neural information processing systems, Palais des Congrès de Montréal, Montréal Canada
Huang, P.-S., He, X., Gao, J., Deng, L., Acero, A., & Heck, L. (2013). Learning Deep Structured Semantic Models for Web Search Using Clickthrough Data. Paper presented at the Proceedings of the 22nd ACM international conference on Information & Knowledge Management, San Francisco, California, USA.
Jansen, B. J., & Rieh, S. Y. (2010). The Seventeen Theoretical Constructs of Information Searching and Information Retrieval. Journal of the American Society for Information Science and Technology, 61(8), 1517-1534.
Jardine, N., & van Rijsbergen, C. J. (1971). The Use of Hierarchic Clustering in Information Retrieval. Information Storage and Retrieval, 7(5), 217-240.
Jozefowicz, R., Zaremba, W., & Sutskever, I. (2015). An Empirical Exploration of Recurrent Network Architectures. Paper presented at the International Conference on Machine Learning, Lille, France.
Khan, F. H., Qamar, U., & Bashir, S. (2016). Multi-Objective Model Selection (MOMS)-based Semi-Supervised Framework for Sentiment Analysis. Cognitive Computation, 8(4), 614-628.
Khanna, A., Pandey, B., Vashishta, K., Kalia, K., Pradeepkumar, B., & Das, T. (2015). A Study of Today’s A.I. Through Chatbots and Rediscovery of Machine Intelligence. International Journal of Service, Science and Technology, 8(7), 277-284.
Kingma, D. P., & Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980.
Mihalcea, R., & Tarau, P. (2004). Textrank: Bringing order into text. Paper presented at the Proceedings of the 2004 conference on empirical methods in natural language processing.
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. Paper presented at the ICLR Workshop, 2013, Scottsdale, AZ, USA.
Mishra, A., & Jain, S. K. (2016). A Survey on Question Answering Systems with Classification. Journal of King Saud University - Computer and Information Sciences, 28(3), 345-361.
Mitra, B., & Craswell, N. (2017). Neural Models for Information Retrieval. arXiv preprint arXiv:1705.01509.
Nallapati, R., Zhou, B., Gulcehre, C., & Xiang, B. (2016). Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond. arXiv preprint arXiv:1602.06023.
Payal, B., Aditi, S., & Nidhi, M. (2014, 7-8 Feb. 2014). A Framework for Restricted Domain Question Answering System. Paper presented at the 2014 International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT), Ghaziabad, India.
Pennington, J., Socher, R., & Manning, C. (2014). Glove: Global Vectors for Word Representation. Paper presented at the Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), Doha, Qatar.
PwC. (2018). 2018 全球與臺灣娛樂暨媒體業展望報告. from https://www.pwc.tw/zh/publications/topic-report/outlook.html
Qin, P., Xu, W., & Guo, J. (2016). An Empirical Convolutional Neural Network Approach for Semantic Relation Classification. Neurocomputing, 190, 1-9.
Radziwill, N. M., & Benton, M. C. (2017). Evaluating Quality of Chatbots and Intelligent Conversational Agents. arXiv preprint arXiv:1704.04579.
Reshmi, S., & Balakrishnan, K. (2016). Implementation of an Inquisitive Chatbot for Database Supported Knowledge Bases. Sādhanā, 41(10), 1173-1178.
Rocktäschel, T., Grefenstette, E., Hermann, K. M., Kočiský, T., & Blunsom, P. (2015). Reasoning About Entailment With Neural Attention. arXiv preprint arXiv:1509.06664.
Ruohonen, J., & Hyrynsalmi, S. (2017). Evaluating the Use of Internet Search Volumes for Time Series Modeling of Sales In the Video Game Industry. Electronic Markets, 27(4), 351-370.
Rush, A. M., Chopra, S., & Weston, J. (2015). A Neural Attention Model for Abstractive Sentence Summarization. arXiv preprint arXiv:1509.00685.
Sagara, T., & Hagiwara, M. (2014). Natural Language Neural Network and its Application to Question-Answering System. Neurocomputing, 142, 201-208.
See, A., Liu, P. J., & Manning, C. D. (2017). Get To The Point: Summarization with Pointer-Generator Networks. arXiv preprint arXiv:1704.04368.
Sharma, Y., & Gupta, S. (2018). Deep Learning Approaches for Question Answering System. Paper presented at the Procedia Computer Science, Gurugram, India.
Shen, Y., He, X., Gao, J., Deng, L., & Grgoire, M. (2014). Learning Semantic Representations Using Convolutional Neural Networks for Web Search. Paper presented at the Proceedings of the 23rd International Conference on World Wide Web, Seoul, Korea.
Shi, T., Keneshloo, Y., Ramakrishnan, N., & Reddy, C. K. (2018). Neural Abstractive Text Summarization with Sequence-to-Sequence Models. arXiv preprint arXiv:1812.02303.
Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to Sequence Learning With Neural Networks. Paper presented at the Advances in neural information processing systems, Palais des Congrès de Montréal, Montréal, CANADA
Wijman, T. (2018). Mobile Revenues Account for More Than 50% of the Global Games Market as It Reaches $137.9 Billion in 2018. from https://newzoo.com/insights/articles/global-games-market-reaches-137-9-billion-in-2018-mobile-games-take-half/
Yang, L., Ai, Q., Guo, J., & Croft, W. B. (2016). aNMM: Ranking Short Answer Texts with Attention-Based Neural Matching Model. Paper presented at the Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, Indianapolis, Indiana, USA.
Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., & Hovy, E. (2016). Hierarchical Attention Networks for Document Classification. Paper presented at the Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, California, USA.
Yu, Q., Lam, W., & Wang, Z. (2018). Responding E-commerce Product Questions via Exploiting QA Collections and Reviews. Paper presented at the Proceedings of the 27th International Conference on Computational Linguistics.
Zhang, Y., Rahman, M. M., Braylan, A., Dang, B., Chang, H.-L., Kim, H., . . . Khetan, V. (2016). Neural Information Retrieval: A Literature Review. arXiv preprint arXiv:1611.06792.
Zhou, X., Hu, B., Chen, Q., & Wang, X. (2018). Recurrent Convolutional Neural Network for Answer Selection in Community Question Answering. Neurocomputing, 274, 8-18.