請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/86162完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 莊裕澤(Yuh-Jzer Joung) | |
| dc.contributor.author | Cheng-En Su | en |
| dc.contributor.author | 蘇成恩 | zh_TW |
| dc.date.accessioned | 2023-03-19T23:39:49Z | - |
| dc.date.copyright | 2022-09-12 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-09-06 | |
| dc.identifier.citation | 宋偲嘉. (2021). 咖啡與憂鬱症之探討. 陳文菁. (2021). 抗憂鬱藥物使用人數. 衛生福利部中央健康保險署.https://data.gov.tw/dataset/146577 李昭慶. (2000). 憂鬱症與運動. 大專體育(50), 82-88. 張家銘. (2020). 台灣憂鬱症就醫現狀與問題. 社團法人臺灣憂鬱症防治協會. http://www.depression.org.tw/knowledge/info.asp?/71.html A+醫學百科. (2011). 支持療法. A+醫學百科. http://cht.a-hospital.com/w/%E6%94%AF%E6%8C%81%E7%96%97%E6%B3%95Harilal, N., Adiwardana, D., Luong, M.-T., So, D. R., Hall, J., Fiedel, N., Thoppilan, R., Yang, Z., Kulshreshtha, A., Nemade, G., & Lu, Y. (2020). Towards a human-like open-domain chatbot. arXiv preprint arXiv:2001.09977. Asghar, N., Poupart, P., Hoey, J., Jiang, X., & Mou, L. (2018). Affective neural response generation. European Conference on Information Retrieval, Cahn, J. (2017). CHATBOT: Architecture, design, & development. University of Pennsylvania School of Engineering and Applied Science Department of Computer and Information Science. Carr, A. (2008). Depression in young people: Description, assessment and evidence-based treatment. Developmental Neurorehabilitation, 11(1), 3-15. Chen, Q., Zhuo, Z., & Wang, W. (2019). Bert for joint intent classification and slot filling. arXiv preprint arXiv:1902.10909. Cho, K., Van Merriënboer, B., 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. 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. Finch, S. E., & Choi, J. D. (2020). Towards unified dialogue system evaluation: A comprehensive analysis of current evaluation protocols. arXiv preprint arXiv:2006.06110. Harilal, N., Shah, R., Sharma, S., & Bhutani, V. (2020). CARO: an empathetic health conversational chatbot for people with major depression. In Proceedings of the 7th ACM IKDD CoDS and 25th COMAD (pp. 349-350). Huang, Y.-H., Lee, S.-R., Ma, M.-Y., Chen, Y.-H., Yu, Y.-W., & Chen, Y.-S. (2019). EmotionX-IDEA: Emotion BERT--an Affectional Model for Conversation. arXiv preprint arXiv:1908.06264. Huang, Y. Y. (2022). Dialogue Analysis of A Chatbot for Patients with Depression Jelinek, F., Mercer, R. L., Bahl, L. R., & Baker, J. K. (1977). Perplexity—a measure of the difficulty of speech recognition tasks. The Journal of the Acoustical Society of America, 62(S1), S63-S63. Li, J., Galley, M., Brockett, C., Spithourakis, G. P., Gao, J., & Dolan, B. (2016). A persona-based neural conversation model. arXiv preprint arXiv:1603.06155. Li, Y., Su, H., Shen, X., Li, W., Cao, Z., & Niu, S. (2017). Dailydialog: A manually labelled multi-turn dialogue dataset. arXiv preprint arXiv:1710.03957. Lin, Z., Madotto, A., Shin, J., Xu, P., & Fung, P. (2019). Moel: Mixture of empathetic listeners. arXiv preprint arXiv:1908.07687. Lin, Z., Xu, P., Winata, G. I., Siddique, F. B., Liu, Z., Shin, J., & Fung, P. (2020). Caire: An end-to-end empathetic chatbot. Proceedings of the AAAI Conference on Artificial Intelligence, Liu, C.-W., Lowe, R., Serban, I. V., Noseworthy, M., Charlin, L., & Pineau, J. (2016). How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation. arXiv preprint arXiv:1603.08023. Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2002). Bleu: a method for automatic evaluation of machine translation. Proceedings of the 40th annual meeting of the Association for Computational Linguistics, Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI blog, 1(8), 9. Ritter, A., Cherry, C., & Dolan, B. (2011). Data-driven response generation in social media. Empirical Methods in Natural Language Processing (EMNLP), Su, H., Jhan, J.-H., Sun, F.-y., Sahay, S., & Lee, H.-y. (2021). Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention. arXiv preprint arXiv:2103.16429. Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. Advances in neural information processing systems, 27. Thase, M. E., Greenhouse, J. B., Frank, E., Reynolds, C. F., Pilkonis, P. A., Hurley, K., Grochocinski, V., & Kupfer, D. J. (1997). Treatment of major depression with psychotherapy or psychotherapy-pharmacotherapy combinations. Archives of general psychiatry, 54(11), 1009-1015. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30. Wolf, T., Sanh, V., Chaumond, J., & Delangue, C. (2019). Transfertransfo: A transfer learning approach for neural network based conversational agents. arXiv preprint arXiv:1901.08149. Zandie, R., & Mahoor, M. H. (2020). Emptransfo: A multi-head transformer architecture for creating empathetic dialog systems. The Thirty-Third International Flairs Conference, Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., & Weston, J. (2018). Personalizing dialogue agents: I have a dog, do you have pets too? arXiv preprint arXiv:1801.07243. Zhang, Y., Sun, S., Galley, M., Chen, Y.-C., Brockett, C., Gao, X., Gao, J., Liu, J., & Dolan, B. (2019). Dialogpt: Large-scale generative pre-training for conversational response generation. arXiv preprint arXiv:1911.00536. 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. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/86162 | - |
| dc.description.abstract | 在現今社會中，儘管憂鬱症病患或是有憂鬱傾向的人越來越多，但憂鬱症病患的求助率卻十分低迷，主要是由於憂鬱症病患缺乏一個良好且即時的聊天管道，加上許多應用在醫療領域的對話系統都著重在解決特定任務上，無法解決憂鬱症病患缺乏聊天管道的難題，而此時能夠理解使用者情緒，並且幫助使用者紓解負面情緒或是給予正面積極的回覆的對話系統就顯得極為重要。 因此本論文與本研究室另一位成員Huang(2022)共同設計一個對話系統，能夠分辨使用者輸入文字的態度、意圖與主題，並且透過這些標籤來進行對話生成，希望藉此來控制模型產生出正面積極且相關的回覆給使用者，來與使用者聊天或是給予建議。 本論文使用強大的GPT-2預訓練模型(pre-trained model)並結合多種標籤來訓練模型，分別對英文對話資料集DailyDialog與由本論文與Huang(2022)所共同建構的中文對答資料集ChinesePsyQA進行實驗，將多種維度標籤加入到對話文本前，藉此讓模型產生出相對應的回覆，而最後在人工評估與自動評估兩種評估方式上，本論文所提出的方法皆比其他生成模型有著更好的表現，說明將多種標籤加入到對話中，可以有效控制模型的生成文本。 | zh_TW |
| dc.description.abstract | In today's society, although there are more and more people with depression or depression tendencies, the help-seeking rate of depression patients is still very low, mainly due to the lack of a good and real-time chat channel for depression patients. In addition, many dialogue systems applied in the medical field focus on solving specific tasks, and cannot solve the problem of lack of chat channels for patients with depression. At this time, a dialogue system that can understand the user's emotions and help users relieve negative emotions or give positive responses is extremely important. Therefore, this paper and another member of our laboratory, Huang (2022), jointly designed a dialogue system that can distinguish the attitude, intentions and topics of the user's input text, and use these tags to generate dialogues, hoping to control the model to produce positive and relevant replies to users, to chat with users or give advice. This paper uses the powerful GPT-2 pre-trained model and combines various labels to train the model. Experiments were carried out on the English dialogue dataset DailyDialog and the Chinese QA dataset ChinesePsyQA jointly constructed by this paper and Huang (2022). Various dimension labels were added before the dialogue text, so that the model can generate corresponding responses. Finally, in the human evaluation and automatic evaluation, the method proposed in this paper has better performance than other generative models, indicating that adding multiple tags to the dialogue can effectively control the generated text of the model. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T23:39:49Z (GMT). No. of bitstreams: 1 U0001-2608202221372800.pdf: 2494292 bytes, checksum: e9a3e8c6324bea0785e3a48f45e67f7c (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 口試委員審定書 i 致謝 ii 中文摘要 iii 英文摘要 iv 圖目錄 vii 表目錄 viii 第一章 緒論 1 1.1 研究背景與動機 1 1.2 研究目的 3 1.3 論文架構 4 第二章 文獻探討 5 2.1 憂鬱症治療 5 2.2 對話系統 6 2.2.1 自然語言理解 7 2.2.2 對話生成 8 2.3 基於GPT模型之對話系統 9 2.4 對話系統評估方法 11 2.4.1 自動評估指標 11 2.4.2 人工評估指標 12 2.4.3 現有評估指標之問題 13 2.5 總結 15 第三章 研究方法 16 3.1 研究架構 16 3.2 資料集 17 3.2.1 DailyDialog 17 3.2.2 ChinesePsyQA 19 3.3 模型架構 21 3.3.1 模型輸入格式 21 3.3.2 GPT-2 DoubleHeads Model 22 3.4 研究驗證方法 25 3.4.1 自動評估 25 3.4.2 人工評估 25 第四章 研究結果 27 4.1 Baseline Models 27 4.2 訓練參數 28 4.3 自動評估結果 28 4.4 人工評估結果 30 4.5 回覆內容分析 31 4.6 對話系統串連 35 4.7 小結 37 第五章 結論 39 5.1 研究成果 39 5.2 研究貢獻 40 5.3 研究限制 40 5.4 未來研究方向 41 參考文獻 43 附錄 47 | |
| dc.language.iso | zh-TW | |
| dc.title | 以憂鬱症病患為對象之多標籤對話生成 | zh_TW |
| dc.title | Multi-label Dialogue Generation for Depression Patients | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳建錦(Chien-Chin Chen),盧信銘(Hsin-Min Lu) | |
| dc.subject.keyword | 憂鬱症,對話生成,預訓練模型,多標籤,深度學習, | zh_TW |
| dc.subject.keyword | Depression,Dialogue Generation,Pre-trained Model,Multi-label,Deep Learning, | en |
| dc.relation.page | 54 | |
| dc.identifier.doi | 10.6342/NTU202202876 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2022-09-06 | |
| dc.contributor.author-college | 管理學院 | zh_TW |
| dc.contributor.author-dept | 資訊管理學研究所 | zh_TW |
| dc.date.embargo-lift | 2022-09-12 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2608202221372800.pdf | 2.44 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。