請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92259
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 傅立成 | zh_TW |
dc.contributor.advisor | Li-Chen Fu | en |
dc.contributor.author | 吳峻銘 | zh_TW |
dc.contributor.author | JUN-MING WU | en |
dc.date.accessioned | 2024-03-21T16:18:37Z | - |
dc.date.available | 2024-03-22 | - |
dc.date.copyright | 2024-03-21 | - |
dc.date.issued | 2024 | - |
dc.date.submitted | 2024-02-04 | - |
dc.identifier.citation | [1] M. A. Conway, “Memory and the self,” Journal of memory and language, vol. 53, no. 4, pp. 594–628, 2005.
[2] W. X. Zhao, K. Zhou, J. Li, T. Tang, X. Wang, Y. Hou, Y. Min, B. Zhang, J. Zhang, Z. Dong et al., “A survey of large language models,” arXiv preprint arXiv:2303.18223, 2023. [3] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017. [4] T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al., “Language models are few-shot learners,” Advances in neural information processing systems, vol. 33, pp. 1877–1901, 2020. [5] J. Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q. V. Le, D. Zhou et al., “Chain-of-thought prompting elicits reasoning in large language models,” Advances in Neural Information Processing Systems, vol. 35, pp. 24 824–24 837, 2022. [6] Y. Gao, Y. Xiong, X. Gao, K. Jia, J. Pan, Y. Bi, Y. Dai, J. Sun, and H. Wang, “Retrieval-augmented generation for large language models: A survey,” arXiv preprint arXiv:2312.10997, 2023. [7] X. Xu, Z. Gou, W. Wu, Z.-Y. Niu, H. Wu, H. Wang, and S. Wang, “Long time no see! open-domain conversation with long-term persona memory,” arXiv preprint arXiv:2203.05797, 2022. [8] “Aging and health,” https://www.who.int/news-room/fact-sheets/detail/ageing-and-health, accessed: 2024-01-30. [9] S. Casaccia, G. M. Revel, L. Scalise, R. Bevilacqua, L. Rossi, R. A. Paauwe, I. Karkowsky, I. Ercoli, J. Artur Serrano, S. Suijkerbuijk et al., “Social robot and sensor network in support of activity of daily living for people with dementia,” in Dementia Lab 2019. Making Design Work: Engaging with Dementia in Context: 4th Conference, D-Lab 2019, Eindhoven, The Netherlands, October 21–22, 2019, Proceedings 4. Springer, 2019, pp. 128–135. [10] C. Neef and A. Richert, “Promoting autonomy in care: combining sensor technology and social robotics for health monitoring,” Engineering Proceedings, vol. 2, no. 1, p. 42, 2020. [11] I. Leite, A. Pereira, G. Castellano, S. Mascarenhas, C. Martinho, and A. Paiva, “Modelling empathy in social robotic companions,” in Advances in User Modeling: UMAP 2011 Workshops, Girona, Spain, July 11-15, 2011, Revised Selected Papers 19. Springer, 2012, pp. 135–147. [12] D. Mazzei, N. Lazzeri, L. Billeci, R. Igliozzi, A. Mancini, A. Ahluwalia, F. Muratori, and D. De Rossi, “Development and evaluation of a social robot platform for therapy in autism,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 2011, pp. 4515–4518. [13] S.-C. Chen, W. Moyle, C. Jones, and H. Petsky, “A social robot intervention on depression, loneliness, and quality of life for taiwanese older adults in long-term care,” International psychogeriatrics, vol. 32, no. 8, pp. 981–991, 2020. [14] S. T. Fiske, A. J. Cuddy, and P. Glick, “Universal dimensions of social cognition: Warmth and competence,” Trends in cognitive sciences, vol. 11, no. 2, pp. 77–83, 2007. [15] M. M. Scheunemann, R. H. Cuijpers, and C. Salge, “Warmth and competence to predict human preference of robot behavior in physical human-robot interaction,” in 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). IEEE, 2020, pp. 1340–1347. [16] Y. Kim, J. Bang, J. Choi, S. Ryu, S. Koo, and G. G. Lee, “Acquisition and use of long-term memory for personalized dialog systems,” in Multimodal Analyses enabling Artificial Agents in Human-Machine Interaction: Second International Workshop, MA3HMI 2014, Held in Conjunction with INTERSPEECH 2014, Singapore, Singapore, September 14, 2014, Revised Selected Papers 2. Springer, 2015, pp. 78–87. [17] Y.-T. Hsiao, E. Gamborino, and L.-C. Fu, “A hybrid conversational agent with semantic association of autobiographic memories for the elderly,” in International Conference on Human-Computer Interaction. Springer, 2020, pp. 53–66. [18] J. Xu, A. Szlam, and J. Weston, “Beyond goldfish memory: Long-term open-domain conversation,” arXiv preprint arXiv:2107.07567, 2021. [19] P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, T. Rocktäschel et al., “Retrieval-augmented generation for knowledge-intensive nlp tasks,” Advances in Neural Information Processing Systems, vol. 33, pp. 9459–9474, 2020. [20] S. Bae, D. Kwak, S. Kang, M. Y. Lee, S. Kim, Y. Jeong, H. Kim, S.-W. Lee, W. Park, and N. Sung, “Keep me updated! memory management in long-term conversations,” arXiv preprint arXiv:2210.08750, 2022. [21] J. Lu, S. An, M. Lin, G. Pergola, Y. He, D. Yin, X. Sun, and Y. Wu, “Memochat: Tuning llms to use memos for consistent long-range open-domain conversation,” arXiv preprint arXiv:2308.08239, 2023. [22] S. Zhang, E. Dinan, J. Urbanek, A. Szlam, D. Kiela, and J. Weston, “Personalizing dialogue agents: I have a dog, do you have pets too?” arXiv preprint arXiv:1801.07243, 2018. [23] Q. Liu, Y. Chen, B. Chen, J.-G. Lou, Z. Chen, B. Zhou, and D. Zhang, “You impress me: Dialogue generation via mutual persona perception,” arXiv preprint arXiv:2004.05388, 2020. [24] B. P. Majumder, H. Jhamtani, T. Berg-Kirkpatrick, and J. McAuley, “Like hiking? you probably enjoy nature: Persona-grounded dialog with commonsense expansions,” arXiv preprint arXiv:2010.03205, 2020. [25] Z. Ma, Z. Dou, Y. Zhu, H. Zhong, and J.-R. Wen, “One chatbot per person: Creating personalized chatbots based on implicit user profiles,” in Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, 2021, pp. 555–564. [26] N. Reimers and I. Gurevych, “Sentence-bert: Sentence embeddings using siamese bert-networks,” arXiv preprint arXiv:1908.10084, 2019. [27] M. A. Conway and C. W. Pleydell-Pearce, “The construction of autobiographical memories in the self-memory system.” Psychological review, vol. 107, no. 2, p. 261, 2000. [28] J. R. Bellegarda, “Statistical language model adaptation: review and perspectives,” Speech communication, vol. 42, no. 1, pp. 93–108, 2004. [29] G. Melis, C. Dyer, and P. Blunsom, “On the state of the art of evaluation in neural language models,” arXiv preprint arXiv:1707.05589, 2017. [30] B. Min, H. Ross, E. Sulem, A. P. B. Veyseh, T. H. Nguyen, O. Sainz, E. Agirre, I. Heintz, and D. Roth, “Recent advances in natural language processing via large pre-trained language models: A survey,” ACM Computing Surveys, vol. 56, no. 2, pp. 1–40, 2023. [31] H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozière, N. Goyal, E. Hambro, F. Azhar et al., “Llama: Open and efficient foundation language models,” arXiv preprint arXiv:2302.13971, 2023. [32] A. Chowdhery, S. Narang, J. Devlin, M. Bosma, G. Mishra, A. Roberts, P. Barham, H. W. Chung, C. Sutton, S. Gehrmann et al., “Palm: Scaling language modeling with pathways,” Journal of Machine Learning Research, vol. 24, no. 240, pp. 1–113, 2023. [33] S. Zhang, S. Roller, N. Goyal, M. Artetxe, M. Chen, S. Chen, C. Dewan, M. Diab, X. Li, X. V. Lin et al., “Opt: Open pre-trained transformer language models,” arXiv preprint arXiv:2205.01068, 2022. [34] J. Wei, Y. Tay, R. Bommasani, C. Raffel, B. Zoph, S. Borgeaud, D. Yogatama, M. Bosma, D. Zhou, D. Metzler et al., “Emergent abilities of large language models,” arXiv preprint arXiv:2206.07682, 2022. [35] M. E. Peters, M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, and L. Zettlemoyer, “Deep contextualized word representations,” CoRR, vol. abs/1802.05365, 2018. [Online]. Available: http://arxiv.org/abs/1802.05365 [36] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018. [37] Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov, “Roberta: A robustly optimized bert pretraining approach,” arXiv preprint arXiv:1907.11692, 2019. [38] Z. Yang, Z. Dai, Y. Yang, J. Carbonell, R. R. Salakhutdinov, and Q. V. Le, “Xl-net: Generalized autoregressive pretraining for language understanding,” Advances in neural information processing systems, vol. 32, 2019. [39] A. Radford and K. Narasimhan, “Improving language understanding by generative pre-training,” 2018. [Online]. Available: https://api.semanticscholar.org/CorpusID:49313245 [40] Y. Zhu, R. Kiros, R. Zemel, R. Salakhutdinov, R. Urtasun, A. Torralba, and S. Fidler, “Aligning books and movies: Towards story-like visual explanations by watching movies and reading books,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 19–27. [41] A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever et al., “Language models are unsupervised multitask learners,” OpenAI blog, vol. 1, no. 8, p. 9, 2019. [42] M. Lewis, Y. Liu, N. Goyal, M. Ghazvininejad, A. Mohamed, O. Levy, V. Stoyanov, and L. Zettlemoyer, “Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension,” arXiv preprint arXiv:1910.13461, 2019. [43] C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu, “Exploring the limits of transfer learning with a unified text-to-text transformer,” The Journal of Machine Learning Research, vol. 21, no. 1, pp. 5485–5551, 2020. [44] X. Wang, J. Wei, D. Schuurmans, Q. Le, E. Chi, S. Narang, A. Chowdhery, and D. Zhou, “Self-consistency improves chain of thought reasoning in language models,” arXiv preprint arXiv:2203.11171, 2022. [45] S. Yao, D. Yu, J. Zhao, I. Shafran, T. L. Griffiths, Y. Cao, and K. Narasimhan, “Tree of thoughts: Deliberate problem solving with large language models,” arXiv preprint arXiv:2305.10601, 2023. [46] 宋豐裕, “基於記憶庫問答的記憶輔助機器人,” Master’s thesis, 國立臺灣大學資訊網路與多媒體研究所, 2023, available at http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87595. [47] D. Antypas, A. Ushio, J. Camacho-Collados, L. Neves, V. Silva, and F. Barbieri, “Twitter topic classification,” arXiv preprint arXiv:2209.09824, 2022. [48] Z. Zhang, X. Han, Z. Liu, X. Jiang, M. Sun, and Q. Liu, “Ernie: Enhanced language representation with informative entities,” arXiv preprint arXiv:1905.07129, 2019. [49] H. Ebbinghaus, “Memory: A contribution to experimental psychology,” Annals of neurosciences, vol. 20, no. 4, p. 155, 2013. [50] Y. Cui, W. Che, T. Liu, B. Qin, S. Wang, and G. Hu, “Revisiting pre-trained models for chinese natural language processing,” arXiv preprint arXiv:2004.13922, 2020. [51] K. Cobbe, V. Kosaraju, M. Bavarian, M. Chen, H. Jun, L. Kaiser, M. Plappert, J. Tworek, J. Hilton, R. Nakano et al., “Training verifiers to solve math word problems,” arXiv preprint arXiv:2110.14168, 2021. [52] J. White, Q. Fu, S. Hays, M. Sandborn, C. Olea, H. Gilbert, A. Elnashar, J. SpencerSmith, and D. C. Schmidt, “A prompt pattern catalog to enhance prompt engineering with chatgpt,” arXiv preprint arXiv:2302.11382, 2023. [53] F. Pezoa, J. L. Reutter, F. Suarez, M. Ugarte, and D. Vrgoč, “Foundations of json schema,” in Proceedings of the 25th international conference on World Wide Web, 2016, pp. 263–273. [54] K. Zhao, W. Liu, J. Luan, M. Gao, L. Qian, H. Teng, and B. Wang, “Unimc: A unified framework for long-term memory conversation via relevance representation learning,” arXiv preprint arXiv:2306.10543, 2023. [55] D. Thulke, N. Daheim, C. Dugast, and H. Ney, “Efficient retrieval augmented generation from unstructured knowledge for task-oriented dialog,” arXiv preprint arXiv:2102.04643, 2021. [56] S. Robertson, H. Zaragoza et al., “The probabilistic relevance framework: Bm25 and beyond,” Foundations and Trends® in Information Retrieval, vol. 3, no. 4, pp.333–389, 2009. [57] R. Ribeiro, J. P. Carvalho, and L. Coheur, “Pgtask: Introducing the task of profile generation from dialogues,” arXiv preprint arXiv:2304.06634, 2023. [58] K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, “Bleu: a method for automatic evaluation of machine translation,” in Proceedings of the 40th annual meeting of the Association for Computational Linguistics, 2002, pp. 311–318. [59] C.-Y. Lin, “Rouge: A package for automatic evaluation of summaries,” in Text summarization branches out, 2004, pp. 74–81. [60] T. Zhang, Y. Liu, B. Li, Z. Zeng, P. Wang, Y. You, C. Miao, and L. Cui, “History-aware hierarchical transformer for multi-session open-domain dialogue system,” arXiv preprint arXiv:2302.00907, 2023. [61] Y. Gu, J. Wen, H. Sun, Y. Song, P. Ke, C. Zheng, Z. Zhang, J. Yao, L. Liu, X. Zhu et al., “Eva2. 0: Investigating open-domain chinese dialogue systems with large-scale pre-training,” Machine Intelligence Research, vol. 20, no. 2, pp. 207–219, 2023. [62] S. Zheng, J. Huang, and K. C.-C. Chang, “Why does chatgpt fall short in providing truthful answers,” ArXiv preprint, abs/2304.10513, 2023. [63] J. Dawes, “Do data characteristics change according to the number of scale points used? an experiment using 5-point, 7-point and 10-point scales,” International journal of market research, vol. 50, no. 1, pp. 61–104, 2008. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92259 | - |
dc.description.abstract | 在社會逐漸進入高齡化老人照護變成一個很重要的議題,然而我們的照護人力往往無法符合社會的需求,因此將機器人導入老人照護領域變成一個有效的做法,老人可以在與機器人交流中得到心靈上的陪伴。
在以往機器人與人類互動的過程中對話是一個很重要的元素,然而現有的人機對話未臻完善,其中一個很大的原因是機器人沒有記憶的能力,導致在長期的互動中機器人不能根據使用者過去所提過的資訊進行個人化的對話。本論文主要提出一個基於自傳式記憶之個人化社交機器人,機器人與使用者對話會以基於自傳式記憶的架構存進我們的記憶庫裡面,在機器人生成回覆前會結合基於變形器編碼的特徵以及階層式自傳式記憶去從記憶庫裡擷取出當前對話上下文最相關的記憶,最後把記憶和對話上下文送進生成模組,在生成模組中我們基於大型語言模型提出了個人化的提示策略以及重排序機制,最後使用者可以得到一個適當的個人化回覆。 在實驗的部分主要分成三個部分,第一個是記憶擷取的實驗,第二個是記憶對話生成的實驗,最後一個是人機互動的實驗,實驗結果顯本系統可以有效擷取過去對話的相關記憶並且可以自然地將記憶融入日常對話中,以此可以讓機器人提供長期個人化的陪伴。 | zh_TW |
dc.description.abstract | In an aging society, elderly care has become an important issue. However, our caregiver workforce often cannot meet the demands of society. Therefore, introducing robots into the field of elderly care has become an effective approach, as the elderly can receive emotional companionship through interactions with robots.
In the process of interaction between robots and humans, conversation is a crucial element. However, existing human-robot conversations are not yet perfect, and a significant reason for this is the lack of memory capabilities in robots. This limitation prevents robots from engaging in personalized conversations based on the past user-provided information during long-term conversations. This thesis proposes a personalized social robot based on autobiographical memory. Conversations between robot and user are stored in our memory bank using an autobiographical memory framework. Before generating a response, the system combines Transformer encoding and hierarchical autobiographical memory to retrieve the most relevant memories based on the current dialogue context. Finally, the memories and conversation context are input into the generative module. In the generative module, we propose a personalized prompting strategy and ranking mechanism based on a large language model. As a result, the user receives an appropriate personalized response. The experimental part of this thesis is divided into three sections: memory retrieval experiments, memory-grounded dialogue generation experiments, and human-robot interaction experiments. Experimental results show that the system can effectively retrieve memories of past conversations and naturally integrate them into everyday conversations, thus allowing the robot to provide long-term personalized companionship. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-03-21T16:18:37Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2024-03-21T16:18:37Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | 口試委員會審定書 i
致謝 ii 摘要 iii Abstract iv Contents vi List of Figures ix List of Tables xi Chapter 1 Introduction 1 1.1 Background 1 1.2 Motivation 2 1.3 Related Work 3 1.3.1 Long-term Memory in Conversation 4 1.3.2 Persona Dialogue 5 1.3.3 Comparison 6 1.4 Objectives and Contributions 7 1.5 Thesis Organization 8 Chapter 2 Preliminaries 10 2.1 Autobiographical Memory 10 2.2 Large Language Model 12 2.2.1 Language Model 15 2.2.2 Pre-trained Language Model 16 2.2.3 Prompt Tuning 19 Chapter 3 Methodology 23 3.1 System Overview 23 3.2 Autobiographical Memory 25 3.2.1 Memory Architecture 25 3.2.2 Memory Construction 27 3.3 Memory Feature Extraction 29 3.3.1 Time Extraction 29 3.3.2 Event Entity Extraction 30 3.3.3 Theme Extraction 34 3.4 Memory Retrieval 35 3.4.1 Memory Feature Matching 37 3.4.2 Memory Ranking 44 3.5 Memory-grounded Response Generation 47 3.5.1 Prompt Management 48 3.5.2 Response Rating 53 Chapter 4 Experiments 56 4.1 Experiment Setting 56 4.1.1 Implementation Details 57 4.1.2 Datasets 58 4.2 Retrieval Experiment 61 4.2.1 Evaluation Metrics 61 4.2.2 Comparison Methods 62 4.2.3 Experimental Results 62 4.2.4 Ablation Study 63 4.2.5 Matching Quality Study 64 4.3 Generation Experiment 65 4.3.1 Evaluation Metrics 65 4.3.2 Comparison Methods 69 4.3.3 Experimental Results 70 4.4 User Study 73 4.4.1 Participants 73 4.4.2 Procedure 73 4.4.3 Questionnaire 74 4.4.4 Experiment Result 74 Chapter 5 Conclusion 79 References 82 | - |
dc.language.iso | en | - |
dc.title | 基於自傳式記憶進行對話之個人化社交機器人 | zh_TW |
dc.title | Personalized Social Robot that chats based on Autobiographical Memory | en |
dc.type | Thesis | - |
dc.date.schoolyear | 112-1 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 岳修平;黃從仁;李宏毅;蘇木春 | zh_TW |
dc.contributor.oralexamcommittee | Hsiu-Ping Yueh;Tsung-Ren Huang;Hung-Yi Lee;Mu-Chun Su | en |
dc.subject.keyword | 大型語言模型,自傳式記憶,人機互動,對話系統,資訊檢索, | zh_TW |
dc.subject.keyword | Large Language Model,Autobiographical Memory,Human-Robot Interaction,Dialogue System,Information Retrieval, | en |
dc.relation.page | 86 | - |
dc.identifier.doi | 10.6342/NTU202400544 | - |
dc.rights.note | 同意授權(限校園內公開) | - |
dc.date.accepted | 2024-02-09 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 資訊工程學系 | - |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-112-1.pdf 目前未授權公開取用 | 5.79 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。