( 您好!臺灣時間:2024/06/16 19:11
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::


研究生(外文):HU, YA-YING
論文名稱(外文):A Dialog Robot with Deep Learning Model for Children Learning English
外文關鍵詞:natural language processingrobot-assisted language learningdeep learningintent recognitionslot filling
  • 被引用被引用:1
  • 點閱點閱:333
  • 評分評分:
  • 下載下載:83
  • 收藏至我的研究室書目清單書目收藏:1
在傳統的課堂學習中,學生都是從課本上閱讀,很少進行對話練習。本研究提出一個自然語言處理之英語對話互動機器人系統,可以讓學生進行英語對話練習。系統架構分為APP端、自然語言處理端及網頁顯示端,APP端設計為教學及對話兩種模式,以圖文並茂方式進行對話情境來學習英語口說能力。而過去對話機器人,在於語音辨識錯誤時缺乏理解學生語句之能力,且無過去記憶功能。本研究為解決以上問題,使用一套開源學習框架-Rasa,利用兩種方式的分類器進行深度學習模型訓練,分別是DIET Classifier以及DIET Classifier with BERT,經過實驗,選擇在識別意圖、實體、插槽填充和對話管理方面有最佳性能,並具有 99% 準確率的DIET Classifier with BERT分類器,藉由插槽填充功能,機器人可以記住當前對話的內容並預測下一步動作。在未來的工作中,將使用擁有抓取物體的機械手臂之物理移動機器人代替模擬機器人,使學習者有更深層次的互動和參與感。
In traditional classroom learning, students read from textbook with little practice of conversation. This research proposes an English dialogue interactive robot with deep learning for natural language processing that can engage students in conversation. The system architecture is composed of an APP on a mobile device, a natural language processing backend and a web page frontend. APP works in a training or a practice mode in a dialogue context with both pictures and texts. Traditional robots do not know how to respond when the learner’s voice cannot be recognized, and generally have no memory of previous dialog. To address these issues, this research employs open source Rasa framework, and two types of classifiers for deep learning training, namely DIET Classifier and DIET Classifier with BERT for performance comparison. After experimentation, the DIET Classifier with BERT model with 99% accuracy is selected for its optimal performance in recognizing intents, entities, filling slots and managing dialogue. With the ability of slot filling, the robot can memorize the content of the current dialogue and predict the next action. In future work, a physical mobile robot with a manipulator for grabbing objects will be used instead of the simulated robot, so that the learner can have a deeper sense of physical interaction and participation.
摘要 i
誌謝 iii
目錄 v
表目錄 viii
圖目錄 ix
第一章、緒論 1
1.1. 研究背景 1
1.2. 研究動機與目的 2
第二章、文獻探討 3
第三章、系統與工具介紹 5
3.1. APP端 5
3.1.1. Xcode 5
3.1.2. Swift語言 5
3.1.3. 語音辨識 6
3.1.4. 硬體規格介紹 6
3.2. 自然語言處理端(後端伺服器) 7
3.2.1. Python語言 7
3.2.2. Flask 7
3.2.3. Rasa框架 8
3.2.4. MySQL 9
3.2.5. NLTK套件 9
3.3. 網頁顯示端 10
3.3.1. JavaScript語言 10
3.3.2. HTML語言 11
3.3.3. CSS 11
3.3.4. Socket 12
3.3.5. Node.js 12
第四章、系統架構及研究方法 13
4.1. 系統架構 13
4.2. APP端流程圖- 教學模式 14
4.3. APP端流程圖- 對話模式 17
4.4. 後端伺服器 19
4.5. 自然語言處理-預處理 20
4.6. 自然語言理解 21
4.6.1. Rasa NLU 21
4.6.2. DIET Classifier 介紹 22
4.6.3. DIET Classifier模型架構 25
4.6.4. BERT介紹 30
4.6.5. DIET Classifier with BERT模型架構 33
4.7. 對話管理 35
4.7.1. Rasa Core介紹 35
4.7.2. Rasa Core訓練架構 36
4.7.3. 追蹤器 41
4.7.4. 解決語音辨識錯誤時的誤判 43
4.8. 模型訓練資訊 44
4.9. 前端網頁顯示端 45
第五章、研究結果與分析 49
5.1. 模型訓練之比較 49
5.2. 針對意圖結果與分析 52
5.3. 針對對話模型結果與分析 55
5.4. 論文比較 56
第六章、結論與未來展望 59
6.1. 結論 59
6.2. 未來展望 59
參考文獻 60
附錄 66

[1]Xu, A., Liu, Z., Guo, Y., Sinha, V., & Akkiraju, R. (2017, May). A new chatbot for customer service on social media. In Proceedings of the 2017 CHI conference on human factors in computing systems (pp. 3506-3510).
[2]Chung, M., Ko, E., Joung, H., & Kim, S. J. (2020). Chatbot e-service and customer satisfaction regarding luxury brands. Journal of Business Research, 117, 587-595.
[3]Nadarzynski, T., Miles, O., Cowie, A., & Ridge, D. (2019). Acceptability of artificial intelligence (AI)-led chatbot services in healthcare: A mixed-methods study. Digital health, 5, 2055207619871808.
[4]Zhou, L., Gao, J., Li, D., & Shum, H. Y. (2020). The design and implementation of xiaoice, an empathetic social chatbot. Computational Linguistics, 46(1), 53-93..
[6]Chen, C. M., & Tsai, Y. N. (2009, July). Interactive location-based game for supporting effective English learning. In 2009 International Conference on Environmental Science and Information Application Technology (Vol. 3, pp. 523-526). IEEE.
[7]Vyawahare, S., & Chakradeo, K. (2020, February). Chatbot Assistant for English as a Second Language Learners. In 2020 International Conference on Convergence to Digital World-Quo Vadis (ICCDW) (pp. 1-5). IEEE.
[8]Muhammad, A. F., Susanto, D., Alimudin, A., Adila, F., Assidiqi, M. H., & Nabhan, S. (2020, September). Developing English Conversation Chatbot Using Dialogflow. In 2020 International Electronics Symposium (IES) (pp. 468-475). IEEE.
[9]Shi, N., Zeng, Q., & Lee, R. (2020, November). Language Chatbot–The Design and Implementation of English Language Transfer Learning Agent Apps. In 2020 IEEE 3rd International Conference on Automation, Electronics and Electrical Engineering (AUTEEE) (pp. 403-407). IEEE.
[10]Srikanthan, P., Nizar, R., Ravikumar, A., Lalitharan, K., Harshanath, S. M. B., & Alosius, J. (2020, October). GLIB: Ameliorated English Skills Development with Artificial Intelligence. In 2020 IEEE Bangalore Humanitarian Technology Conference (B-HTC) (pp. 1-6). IEEE.
[11]Kasthuri, E., & Balaji, S. (2021, February). A Chatbot for Changing Lifestyle in Education. In 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV) (pp. 1317-1322). IEEE.
[12]Serrano, J., Gonzalez, F., & Zalewski, J. (2015, September). CleverNAO: The intelligent conversational humanoid robot. In 2015 IEEE 8th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS) (Vol. 2, pp. 887-892). IEEE.
[13]Prajwal, S. V., Mamatha, G., Ravi, P., Manoj, D., & Joisa, S. K. (2019, November). Universal semantic web assistant based on sequence to sequence model and natural language understanding. In 2019 9th International Conference on Advances in Computing and Communication (ICACC) (pp. 110-115). IEEE.
[14]Chowdhury, G. G. (2003). Natural language processing. Annual review of information science and technology, 37(1), 51-89.
[15]Malik, K. M., Javed, A., Malik, H., & Irtaza, A. (2020). A light-weight replay detection framework for voice controlled IoT devices. IEEE Journal of Selected Topics in Signal Processing, 14(5), 982-996.
[16]Mahima, Y., & Ginige, T. N. D. S. (2020, November). Graph and Natural Language Processing Based Recommendation System for Choosing Machine Learning Algorithms. In 2020 12th International Conference on Advanced Infocomm Technology (ICAIT) (pp. 119-123). IEEE.
[17]Adhikar, S. (2020, March). NLP based Machine Learning Approaches for Text Summarization. In 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC) (pp. 535-538). IEEE.
[18]Tur, G., & De Mori, R. (2011). Spoken language understanding: Systems for extracting semantic information from speech. John Wiley & Sons.
[19]Zhang, J. (2020, April). CLEMENT: Machine Learning Methods for Malware Recognition Based on Semantic Behaviours. In 2020 International Conference on Computer Information and Big Data Applications (CIBDA) (pp. 233-236). IEEE.
[20]Hakkani-Tür, D., Tür, G., Celikyilmaz, A., Chen, Y. N., Gao, J., Deng, L., & Wang, Y. Y. (2016, September). Multi-domain joint semantic frame parsing using bi-directional rnn-lstm. In Interspeech (pp. 715-719).
[21]Shantala, R., Kyselov, G., & Kyselova, A. (2018, October). Neural dialogue system with emotion embeddings. In 2018 IEEE First International Conference on System Analysis & Intelligent Computing (SAIC) (pp. 1-4). IEEE.
[22]Jia, Y., Min, G., Xu, C., Li, X., & Zhang, D. (2020). A Knowledge Driven Dialogue Model With Reinforcement Learning. IEEE Access, 8, 131741-131749.
[23]Bocklisch, T., Faulkner, J., Pawlowski, N., & Nichol, A. (2017). Rasa: Open source language understanding and dialogue management. arXiv preprint arXiv:1712.05181.
[24]Gamage, B., Pushpananda, R., & Weerasinghe, R. (2020, November). The impact of using pre-trained word embeddings in Sinhala chatbots. In 2020 20th International Conference on Advances in ICT for Emerging Regions (ICTer) (pp. 161-165). IEEE.
[25]Sun, C., Myers, A., Vondrick, C., Murphy, K., & Schmid, C. (2019). Videobert: A joint model for video and language representation learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 7464-7473).
[26]Goutte, C., & Gaussier, E. (2005, March). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In European conference on information retrieval (pp. 345-359). Springer, Berlin, Heidelberg.
[27]Vogelsang, D. C., & Erickson, B. J. (2020). Magician’s corner: 6. TensorFlow and TensorBoard.
[28]Muhammad, A. F., Pratama, D. E., & Alimudin, A. (2019, September). Development of Web Based Application with Speech Recognition As English Learning Conversation Training Media. In 2019 International Electronics Symposium (IES) (pp. 571-576). IEEE.
[30]Lafferty, J., McCallum, A., & Pereira, F. C. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data.
[31]Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., & Dyer, C. (2016). Neural architectures for named entity recognition. arXiv preprint arXiv:1603.01360.
[32]Bunk, T., Varshneya, D., Vlasov, V., & Nichol, A. (2020). Diet: Lightweight language understanding for dialogue systems. arXiv preprint arXiv:2004.09936.
[33]Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
[34]Khorashadizadeh, H., Monsefi, R., & Foolad, S. (2020, September). Attention-based Convolutional Neural Network for Answer Selection using BERT. In 2020 8th Iranian Joint Congress on Fuzzy and intelligent Systems (CFIS) (pp. 121-126). IEEE.
[35]Chen, P. J., Hsu, I. H., Huang, Y. Y., & Lee, H. Y. (2017, December). Mitigating the impact of speech recognition errors on chatbot using sequence-to-sequence model. In 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (pp. 497-503). IEEE.
[36]Feng, F., Yang, Y., Cer, D., Arivazhagan, N., & Wang, W. (2020). Language-agnostic bert sentence embedding. arXiv preprint arXiv:2007.01852.
[37]Vlasov, V., Mosig, J. E., & Nichol, A. (2019). Dialogue transformers. arXiv preprint arXiv:1910.00486.
[39]Goutte, C., & Gaussier, E. (2005, March). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In European conference on information retrieval (pp. 345-359). Springer, Berlin, Heidelberg.
[40]Das, S., & Kumar, E. (2018, December). Determining accuracy of chatbot by applying algorithm design and defined process. In 2018 4th International Conference on Computing Communication and Automation (ICCCA) (pp. 1-6). IEEE.
[41]Bathija, R., Agarwal, P., Somanna, R., & Pallavi, G. B. (2020, March). Guided interactive learning through chatbot using bi-directional encoder representations from transformers (bert). In 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA) (pp. 82-87). IEEE.
[42]Khanlari, A. (2016, October). Long term effects of educational robots on a Grade 9 girl's perceptions of science and math. In 2016 IEEE Frontiers in Education Conference (FIE) (pp. 1-4). IEEE.

第一頁 上一頁 下一頁 最後一頁 top