近年英語學習的影片、網頁或是軟體如雨後春筍不斷出現，數位教育與網路學習的商機越來越龐大。而隨著使用科技產品的人數比例提升，對話機器人也是不斷地發展成長。本論文期望跨領域的結合，讓使用者在與機器人對話中學習英語，以達到教學的目的。
與一般對話任務不同，本系統為了協助使用者學習，加入針對於學習的意圖，分析使用者可能需要協助。並且為了更有效地輔助使用者學習，本系統能根據使用者評估結果、使用者歷史資訊動態地調整文本生成的策略，以生成多元的回覆語句。
本論文的主要貢獻如下：1. 建立餐廳英語教學情境的對話機器人，透過語句生成生成多元的協助回覆。2. 分析對話內容，了解使用者各種意圖，其中包含「聽不懂」等不同情況。
實驗結果顯示，此系統的理解核心能正確分析出 90% 語句的意圖。而其中有 87.25% 語句能抽取出該意圖的腳本所需的槽位值來完成機器人回覆所需資料。我們也透過問卷調查的方式來收集使用者回饋，其中 SUS 系統可用性評分為 65.68，已經非常接近可接受的 68 分，顯示本系統已經具有一定的成效。

In recent years, there are many videos, websites, and software for learning English. Therefore, the business opportunities of digital education and e-learning are getting more and more. As the proportion of people using mobile devices increases, the field of the dialogue system continues to develop and grow. This thesis aims to combine the cross-disciplinary approach so that users can learn English in conversation with robots.
Different from the normal task-oriented dialogue system, in order to help users learn English, we add some intents for teaching needs and analyze the user sentences to detect when users need assistance.Moreover, to assist users more effectively, the text generation strategy is dynamically adjusted based on user evaluation results and history information.
The main contributions of this thesis are:1. Establishing a dialogue system in an English teaching scenario of restaurant, generating multiple responses through text generation. 2. Analyze the conversation to understand the user ’s various intents, including different situations such as ”don’t understand”.
The experimental results show that the comprehension core of this system can correctly analyze 90% of the sentences. 87.25% of the sentences are able to extract the required slot value to complete the system’s response. We also collected users’ feedback through a questionnaire survey, in which the SUS system usability score was 65.68. It is very close to the acceptable score of 68, indicating that the system is already effective.

[1] K. R. Chowdhary, “Natural language processing,” in Fundamentals of Artificial Intelligence, pp. 603–649, 2020.
[2] S. Arora, K. Batra, and S. Singh, “Dialogue system: A brief review,” 2013.
[3] H. Chen, X. Liu, D. Yin, and J. Tang, “A survey on dialogue systems: Recent advances and new frontiers,” SIGKDD Explor. Newsl., vol. 19, p. 25–35, nov 2017.
[4] W.-H. Wu, Y.-C. Jim Wu, C.-Y. Chen, H.-Y. Kao, C.-H. Lin, and S.H. Huang, “Review of trends from mobile learning studies: A meta-analysis,” Computers Education, vol. 59, no. 2, pp. 817–827, 2012.
[5] J. Gao, M. Galley, L. Li, et al., “Neural approaches to conversational ai,” Foundations and trends® in information retrieval, vol. 13, no. 2-3, pp. 127–298, 2019.
[6] Z. Zhang, R. Takanobu, Q. Zhu, M. Huang, and X. Zhu, “Recent advances and challenges in task-oriented dialog systems,” Science China Technological Sciences, vol. 63, no. 10, pp. 2011–2027, 2020.
[7] M. Warschauer and D. Healey, “Computers and language learning: an overview,” Language Teaching, vol. 31, no. 2, p. 57–71, 1998.
[8] W. Alshalan, “Mobile assisted language learning: A literature review,” Journal of Humanities and Social Sciences, vol. 03, pp. 93–97, 01 2019.
[9] D. Reddy, “Speech recognition by machine: A review,” Proceedings of the IEEE, vol. 64, no. 4, pp. 501–531, 1976.
[10] A. B. Nassif, I. Shahin, I. Attili, M. Azzeh, and K. Shaalan, “Speech recognition using deep neural networks: A systematic review,” IEEE Access, vol. 7, pp. 19143–19165, 2019.
[11] K. Zimmerman, “A literature review of the challenges & best practices for english language learners,” in National forum of multicultural issues journal, vol. 11, pp. 1–7, 2014.
[12] M. Alt, G. D. Arizmendi, C. R. Beal, and J. S. Hurtado, “The effect of test translation on the performance of
second grade english learners on the keymath-3,” Psychology in the Schools, vol. 50, no. 1, pp. 27–36, 2013.
[13] M. SWAIN and S. LAPKIN, “Problems in output and the cognitive processes they generate: A step towards second language learning,”Applied Linguistics, vol. 16, pp. 371–391, 09 1995.
[14] C. Nass, J. Steuer, and E. R. Tauber, “Computers are social actors,” in Proceedings of the SIGCHI conference on Human factors in computing systems, pp. 72–78, 1994.
[15] F. G. Escobar Fandiño, L. D. Muñoz, and A. J. Silva Velandia “Motivation and e-learning english as a foreign language: A qualitative study,” Heliyon, vol. 5, no. 9, p. e02394, 2019.
[16] M. K. Kabilan, N. Ahmad, and M. J. Z. Abidin, “Facebook: An online environment for learning of english in institutions of higher education?,” The Internet and higher education, vol. 13, no. 4, pp. 179–187, 2010.
[17] R.-C. Shih, “Effect of using facebook to assist english for business communication course instruction.,” Turkish Online Journal of Educational Technology-TOJET, vol. 12, no. 1, pp. 52–59, 2013.
[18] A. O. AbuSa＇aleek et al., “Students＇perceptions of english language learning in the facebook context,” Teaching English with Technology, vol. 15, no. 4, pp. 60–75, 2015.
[19] Z.-J. You, C.-Y. Shen, C.-W. Chang, B.-J. Liu, and G.-D. Chen, “A robot as a teaching assistant in an english class,” in Sixth IEEE International Conference on Advanced Learning Technologies, pp. 87–91, 2006.
[20] C.-M. Chen and Y.-L. Li, “Personalised context-aware ubiquitous learning system for supporting effective english vocabulary learning,”Interactive Learning Environments, vol. 18, no. 4, pp. 341–364, 2010.
[21] M. Nushi and M. H. Eqbali, “Duolingo: A mobile application to assist second language learning.,” Teaching English with Technology, vol. 17, no. 1, pp. 89–98, 2017.
[22] Z.-H. Chen and S.-Y. Lee, “Application-driven educational game to assist young children in learning english vocabulary,” Journal of Educational Technology & Society, vol. 21, no. 1, pp. 70–81, 2018.
[23] K.-C. Li, M. Chang, and K.-H. Wu, “Developing a task-based dialogue system for english language learning,” Education Sciences, vol. 10, no. 11, p. 306, 2020.
[24] X. L. Pham, T. Pham, Q. M. Nguyen, T. H. Nguyen, and T. T. H. Cao, “Chatbot as an intelligent personal assistant for mobile language learning,” in Proceedings of the 2018 2nd International Conference on Education and E-Learning, p. 16–21, Association for Computing Machinery, 2018.
[25] A. I. Rudnicky, E. H. Thayer, P. C. Constantinides, C. Tchou, R. Shern, K. A. Lenzo, W. Xu, and A. Oh, “Creating natural dialogs in the carnegie mellon communicator system.,” in Eurospeech, 1999.
[26] X. Wang and C. Yuan, “Recent advances on human-computer dialogue,” CAAI Transactions on Intelligence Technology, vol. 1, no. 4, pp. 303–312, 2016.
[27] I. Serban, A. Sordoni, Y. Bengio, A. Courville, and J. Pineau, “Building end-to-end dialogue systems using generative hierarchical neural network models,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30, 2016.
[28] T. Young, E. Cambria, I. Chaturvedi, H. Zhou, S. Biswas, and M. Huang, “Augmenting end-to-end dialogue systems with commonsense knowledge,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, 2018.
[29] X. Li, Y.-N. Chen, L. Li, J. Gao, and A. Celikyilmaz, “End-to-end task-completion neural dialogue systems,” arXiv preprint arXiv:1703.01008, 2017.
[30] B. Liu, G. Tur, D. Hakkani-Tur, P. Shah, and L. Heck, “Dialogue learning with human teaching and feedback in end-to-end trainable task-oriented dialogue systems,” arXiv preprint arXiv:1804.06512, 2018.
[31] T.-H. Wen, D. Vandyke, N. Mrksic, M. Gasic, L. M. Rojas-Barahona, P.-H. Su, S. Ultes, and S. Young, “A network-based end-to-end trainable task-oriented dialogue system,” arXiv preprint arXiv:1604.04562, 2016.
[32] A. Bordes, Y.-L. Boureau, and J. Weston, “Learning end-to-end goal-oriented dialog,” arXiv preprint arXiv:1605.07683, 2016.
[33] W. Lei, X. Jin, M.-Y. Kan, Z. Ren, X. He, and D. Yin, “Sequicity: Simplifying task-oriented dialogue systems with single sequence-to-sequence architectures,” in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1437–1447, 2018.
[34] T. Zhao and M. Eskenazi, “Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning,” in Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 1–10, Association for Computational Linguistics, Sept. 2016.
[35] I. Muslea et al., “Extraction patterns for information extraction tasks: A survey,” in The AAAI-99 workshop on machine learning for information extraction, vol. 2, 1999.
[36] D. C. Wimalasuriya and D. Dou, “Ontology-based information extraction: An introduction and a survey of current approaches,”Journal of Information Science, vol. 36, no. 3, pp. 306–323, 2010.
[37] J. Liu, Y. Li, and M. Lin, “Review of intent detection methods in the human-machine dialogue system,” vol. 1267, p. 012059, jul 2019.
[38] J. Dowding, J. M. Gawron, D. Appelt, J. Bear, L. Cherny, R. Moore, and D. Moran, “Gemini: A natural language system for spoken-language understanding,” arXiv preprint cmp-lg/9407007, 1994.
[39] H. B. Hashemi, A. Asiaee, and R. Kraft, “Query intent detection using convolutional neural networks,” in International Conference on Web Search and Data Mining, Workshop on Query Understanding, 2016.
[40] I. Casanueva, T. Temčinas, D. Gerz, M. Henderson, and I. Vulić, “Efficient intent detection with dual sentence encoders,” arXiv preprint arXiv:2003.04807, 2020.
[41] L. Qin, W. Che, Y. Li, H. Wen, and T. Liu, “A stack-propagation framework with token-level intent detection for spoken language understanding,” in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp. 2078–2087, 2019.
[42] T.-W. Wu, R. Su, and B. Juang, “A label-aware bert attention network for zero-shot multi-intent detection in spoken language understanding,” in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 4884–4896, 2021.
[43] Y. Xian, B. Schiele, and Z. Akata, “Zero-shot learning-the good, the bad and the ugly,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4582–4591, 2017.
[44] W. Wang, V. W. Zheng, H. Yu, and C. Miao, “A survey of zero-shot learning: Settings, methods, and applications,” ACM Transactions on Intelligent Systems and Technology(TIST), vol. 10, no. 2, pp. 1–37, 2019.
[45] Y. Wang, Q. Yao, J. T. Kwok, and L. M. Ni, “Generalizing from a few examples: A survey on few-shot learning,” ACM computing surveys (csur), vol. 53, no. 3, pp. 1–34, 2020.
[46] R. Sarikaya, A. Celikyilmaz, A. Deoras, and M. Jeong, “Shrinkage based features for slot tagging with conditional random fields,” in Fifteenth Annual Conference of the International Speech Communication Association, 2014.
[47] K. Yao, G. Zweig, M.-Y. Hwang, Y. Shi, and D. Yu “Recurrent neural networks for language understanding.,” in Interspeech, pp. 2524–2528, 2013.
[48] G. Mesnil, Y. Dauphin, K. Yao, Y. Bengio, L. Deng, D. Hakkani-Tur, X. He, L. Heck, G. Tur, D. Yu, and G. Zweig, “Using recurrent neural networks for slot filling in spoken language understanding,”IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol.23, no. 3, pp. 530–539, 2015.
[49] G. Kurata, B. Xiang, B. Zhou, and M. Yu, “Leveraging sentence level information with encoder lstm for semantic slot filling,” in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 2077–2083, 2016.
[50] Z. Liu, G. I. Winata, P. Xu, and P. Fung, “Coach: A coarse-to-fine approach for cross-domain slot filling,” in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 19–25, Association for Computational Linguistics, July 2020.
[51] 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), pp. 1777–1788, 2017.
[52] L. Ren, K. Xie, L. Chen, and K. Yu, “Towards universal dialogue state tracking,” in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2780–2786, Association for Computational Linguistics, Oct.-Nov. 2018.
[53] S. Kim, S. Yang, G. Kim, and S.-W. Lee, “Efficient dialogue state tracking by selectively overwriting memory,” in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 567–582, 2020.
[54] Z. Yan, N. Duan, P. Chen, M. Zhou, J. Zhou, and Z. Li, “Building task-oriented dialogue systems for online shopping,” in Thirty-first AAAI conference on artificial intelligence, 2017.
[55] B. Peng, X. Li, J. Gao, J. Liu, and K.-F. Wong, “Deep dyna-q: Integrating planning for task-completion dialogue policy learning,” in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2182–2192, 2018.
[56] X. Liu, J. Gao, X. He, L. Deng, K. Duh, and Y.-Y. Wang “Representation learning using multi-task deep neural networks for semantic classification and information retrieval,” in Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 912–921, 2015.
[57] B. Peng, X. Li, L. Li, J. Gao, A. Celikyilmaz, S. Lee, and K.-F. Wong, “Composite task-completion dialogue policy learning via hierarchical deep reinforcement learning,” in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2231–2240, Association for Computational Linguistics, Sept. 2017.
[58] B. Peng, X. Li, J. Gao, J. Liu, Y.-N. Chen, and K.-F. Wong “Adversarial advantage actor-critic model for task-completion dialogue policy learning,” in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6149–6153, 2018.
[59] O. Lemon, “Learning what to say and how to say it: Joint optimisation of spoken dialogue management and natural language generation,” Computer Speech & Language, vol. 25, no. 2, pp. 210–221, 2011.
[60] M. Kale and A. Rastogi, “Template guided text generation for task-oriented dialogue,” arXiv preprint arXiv:2004.15006, 2020.
[61] J. Li, W. Monroe, T. Shi, S. Jean, A. Ritter, and D. Jurafsky “Adversarial learning for neural dialogue generation,” in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2157–2169, 2017.
[62] T.-H. Wen, M. Gašić, N. Mrkšić, P.-H. Su, D. Vandyke, and S. Young, “Semantically conditioned LSTM-based natural language generation for spoken dialogue systems,” in Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1711–1721, Association for Computational Linguistics, Sept. 2015.
[63] T.-H. Wen, M. Gašić, D. Kim, N. Mrkšić, P.-H. Su, D. Vandyke, and S. Young, “Stochastic language generation in dialogue using recurrent neural networks with convolutional sentence reranking,” in Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 275–284, Association for Computational Linguistics, Sept. 2015.
[64] Y. Fan, X. Luo, and P. Lin, “A survey of response generation of dialogue systems,” International Journal of Computer and Information Engineering, vol. 14, no. 12, pp. 461 – 472, 2020.
[65] N. Guarino, D. Oberle, and S. Staab, “What is an ontology?,” in Handbook on ontologies, pp. 1–17, Springer, 2009.
[66] W.-L. Hsu, S.-H. Wu, and Y.-S. Chen, “Event identification based on the information map-infomap,” in 2001 IEEE International Conference on Systems, Man and Cybernetics. e-Systems and e-Man for Cybernetics in Cyberspace, vol. 3, pp. 1661–1666 vol.3, 2001.
[67] M.-Y. Day, R. T.-H. Tsai, C.-L. Sung, C.-C. Hsieh, C.-W. Lee, S.-H. Wu, K.-P. Wu, C.-S. Ong, and W.-L. Hsu, “Reference metadata extraction using a hierarchical knowledge representation framework, Decision Support Systems, vol. 43, no. 1, pp. 152–167, 2007.
[68] W.-L. Hsu, “Statistical pattern generation for information extraction,” Feb. 11 2020. US Patent 10,558,926.
[69] P.-T. Lai, M.-S. Huang, T.-H. Yang, W.-L. Hsu, and R. T.-H. Tsai,“Statistical principle-based approach for gene and protein related object recognition,” Journal of cheminformatics, vol. 10, no. 1, pp. 1–9, 2018.
[70] H.-J. Dai, C.-K. Wang, N.-W. Chang, M.-S. Huang, J. Jonnagaddala, F.-D. Wang, and W.-L. Hsu, “Statistical principle-based approach for recognizing and normalizing micrornas described in scientific literature,” Database, vol. 2019, 2019.
[71] 張乃文, “基於統計準則式方法偵測生醫文獻中的生物關聯,” 博士論文，國立臺灣 大學生醫電子與資訊學研究所, 2020.
[72] 許聞廉, “一個全新的自然語言模型 principle-based approach,” IR Workshop 2021, 2021.
[73] A. Bangor, P. Kortum, and J. Miller, “Determining what individual sus scores mean: Adding an adjective rating scale,” Journal of usability studies, vol. 4, no. 3, pp. 114–123, 2009.