請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/101135完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳尚澤 | zh_TW |
| dc.contributor.advisor | Shang-Tse Chen | en |
| dc.contributor.author | 戚得郁 | zh_TW |
| dc.contributor.author | Te-Yu Chi | en |
| dc.date.accessioned | 2025-12-31T16:04:08Z | - |
| dc.date.available | 2026-01-01 | - |
| dc.date.copyright | 2025-12-31 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-12-30 | - |
| dc.identifier.citation | Ollama official website. https://ollama.com/. Accessed: 2025-02-26.
Haisal Dauda Abubakar, Mahmood Umar, and Muhammad Abdullahi Bakale. Sentiment classification: Review of text vectorization methods: Bag of words, tf-idf, word2vec and doc2vec. SLU Journal of Science and Technology, 4(1):27–33, 2022. Akiko Aizawa. An information-theoretic perspective of tf–idf measures. Information Processing & Management, 39(1):45–65, 2003. Issa Annamoradnejad. Colbert: Using BERT sentence embedding for humor detection. CoRR, abs/2004.12765, 2020. URL https://arxiv.org/abs/2004.12765. Sören Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak, and Zachary Ives. Dbpedia: A nucleus for a web of open data. In Karl Aberer, Key-Sun Choi, Natasha Noy, Dean Allemang, Kyung-Il Lee, Lyndon Nixon, Jennifer Golbeck, Peter Mika, Diana Maynard, Riichiro Mizoguchi, Guus Schreiber, and Philippe Cudré-Mauroux, editors, The Semantic Web, pages 722–735, Berlin, Heidelberg, 2007. Springer Berlin Heidelberg. ISBN 978-3-540-76298-0. Tom B Brown. Language models are few-shot learners. arXiv preprint arXiv:2005.14165, 2020. Dhivya Chandrasekaran and Vijay Mago. Evolution of semantic similarity—a survey. ACM Computing Surveys (CSUR), 54(2):1–37, 2021. Ming-Wei Chang, Lev-Arie Ratinov, Dan Roth, and Vivek Srikumar. Importance of semantic representation: Dataless classification. In Aaai, volume 2, pages 830–835, 2008. Te-Yu Chi and Jyh-Shing Roger Jang. Wc-sbert: Zero-shot topic classification using sbert and light self-training on wikipedia categories. ACM Transactions on Intelligent Systems and Technology, 15(5):1–18, 2024. Zewei Chu, Karl Stratos, and Kevin Gimpel. Natcat: Weakly supervised text classification with naturally annotated datasets. CoRR, abs/2009.14335, 2020. URL https://arxiv.org/abs/2009.14335. Jacob Devlin. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018. Hantian Ding, Jinrui Yang, Yuqian Deng, Hongming Zhang, and Dan Roth. Towards open-domain topic classification. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations, pages 90–98, Hybrid: Seattle, Washington + Online, July 2022. Association for Computational Linguistics. doi: 10.18653/v1/2022. naacl-demo.10. URL https://aclanthology.org/2022.naacl-demo.10. Christiane Fellbaum. Wordnet. In Theory and applications of ontology: computer applications, pages 231–243. Springer, 2010. Luciano Floridi and Massimo Chiriatti. Gpt-3: Its nature, scope, limits, and consequences. Minds and Machines, 30:681–694, 2020. Tianyu Gao, Xingcheng Yao, and Danqi Chen. Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821, 2021. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, and Haofen Wang. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, 2023. Ariel Gera, Alon Halfon, Eyal Shnarch, Yotam Perlitz, Liat Ein-Dor, and Noam Slonim. Zero-shot text classification with self-training. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1107–1119, Abu Dhabi, United Arab Emirates, December 2022. Association for Computational Linguistics. URL https://aclanthology.org/2022.emnlp-main.73. Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W Mahoney, and Kurt Keutzer. A survey of quantization methods for efficient neural network inference. In Low-power computer vision, pages 291–326. Chapman and Hall/CRC, 2022. Louie Giray. Prompt engineering with chatgpt: a guide for academic writers. Annals of biomedical engineering, 51(12):2629–2633, 2023. Alex Graves and Alex Graves. Long short-term memory. Supervised sequence labelling with recurrent neural networks, pages 37–45, 2012. Yaakov HaCohen-Kerner, Daniel Miller, and Yair Yigal. The influence of preprocessing on text classification using a bag-of-words representation. PloS one, 15(5):e0232525, 2020. Charles R. Harris, K. Jarrod Millman, Stéfan J. van der Walt, Ralf Gommers, Pauli Virtanen, David Cournapeau, Eric Wieser, Julian Taylor, Sebastian Berg, Nathaniel J. Smith, Robert Kern, Matti Picus, Stephan Hoyer, Marten H. van Kerkwijk, Matthew Brett, Allan Haldane, Jaime Fernández del Río, Mark Wiebe, Pearu Peterson, Pierre Gérard-Marchant, Kevin Sheppard, Tyler Reddy, Warren Weckesser, Hameer Abbasi, Christoph Gohlke, and Travis E. Oliphant. Array programming with NumPy. Nature, 585(7825):357–362, September 2020. doi: 10.1038/s41586-020-2649-2. URL https://doi.org/10.1038/s41586-020-2649-2. Andres Hat. Llm quantization naming explained. https://andreshat.medium.com/ llm-quantization-naming-explained-bedde33f7192. Accessed: 2025-02-26. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12):1–38, 2023. T Joachims. Text categorization with support vector machines: Learning with many relevant features, 1998. Katikapalli Subramanyam Kalyan. A survey of gpt-3 family large language models including chatgpt and gpt-4. Natural Language Processing Journal, page 100048, 2023. Darioush Kevian, Usman Syed, Xingang Guo, Aaron Havens, Geir Dullerud, Peter Seiler, Lianhui Qin, and Bin Hu. Capabilities of large language models in control engineering: A benchmark study on gpt-4, claude 3 opus, and gemini 1.0 ultra. arXiv preprint arXiv:2404.03647, 2024. Yoon Kim. Convolutional neural networks for sentence classification. CoRR, abs/ 1408.5882, 2014. URL http://arxiv.org/abs/1408.5882. David G Kleinbaum, K Dietz, M Gail, Mitchel Klein, and Mitchell Klein. Logistic regression. Springer, 2002. Elad Levi, Eli Brosh, and Matan Friedmann. Intent-based prompt calibration: Enhancing prompt optimization with synthetic boundary cases, 2024. Chaoqun Liu, Wenxuan Zhang, Guizhen Chen, Xiaobao Wu, Anh Tuan Luu, Chip Hong Chang, and Lidong Bing. Zero-shot text classification via self-supervised tuning, 2023. Yinhan Liu. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019. Andrew McCallum, Kamal Nigam, et al. A comparison of event models for naive bayes text classification. In AAAI-98 workshop on learning for text categorization, volume 752, pages 41–48. Madison, WI, 1998. Tomas Mikolov, Martin Karafiát, Lukas Burget, Jan Cernockỳ, and Sanjeev Khudanpur. Recurrent neural network based language model. In Interspeech, volume 2, pages 1045– 1048. Makuhari, 2010. Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y Ng. Multimodal deep learning. In Proceedings of the 28th international conference on machine learning (ICML-11), pages 689–696, 2011. Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, and Jianfeng Gao. Instruction tuning with gpt-4. arXiv preprint arXiv:2304.03277, 2023. Juan Ramos et al. Using tf-idf to determine word relevance in document queries. In Proceedings of the first instructional conference on machine learning, volume 242, pages 29–48. Citeseer, 2003. Nils Reimers and Iryna Gurevych. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 11 2019. URL http://arxiv.org/abs/1908.10084. V Sanh. Distilbert, a distilled version of bert: Smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108, 2019. Fabrizio Sebastiani. Machine learning in automated text categorization. ACM computing surveys (CSUR), 34(1):1–47, 2002. Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. Mpnet: Masked and permuted pre-training for language understanding. Advances in neural information processing systems, 33:16857–16867, 2020. Robyn Speer, Joshua Chin, and Catherine Havasi. Conceptnet 5.5: An open multilingual graph of general knowledge. CoRR, abs/1612.03975, 2016. URL http://arxiv. org/abs/1612.03975. Emma Strubell, Ananya Ganesh, and Andrew McCallum. Energy and policy considerations for modern deep learning research. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 13693–13696, 2020. Gemini Team, Rohan Anil, Sebastian Borgeaud, Yonghui Wu, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, et al. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805, 2023. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023. Albert Tseng, Jerry Chee, Qingyao Sun, Volodymyr Kuleshov, and Christopher De Sa. Quip#: Even better llm quantization with hadamard incoherence and lattice codebooks. arXiv preprint arXiv:2402.04396, 2024. Albert Tseng, Qingyao Sun, David Hou, and Christopher M De Sa. Qtip: Quantization with trellises and incoherence processing. Advances in Neural Information Processing Systems, 37:59597–59620, 2025. Mozes van de Kar, Mengzhou Xia, Danqi Chen, and Mikel Artetxe. Don’t prompt, search! mining-based zero-shot learning with language models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7508–7520, Abu Dhabi, United Arab Emirates, December 2022. Association for Computational Linguistics. URL https://aclanthology.org/2022.emnlp-main.509. A Vaswani. Attention is all you need. Advances in Neural Information Processing Systems, 2017. Olivia Weng. Neural network quantization for efficient inference: A survey. arXiv preprint arXiv:2112.06126, 2021. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, and Jamie Brew. Huggingface’s transformers: State-of-the-art natural language processing. CoRR, abs/ 1910.03771, 2019. URL http://arxiv.org/abs/1910.03771. Peng Xu, Xiatian Zhu, and David A Clifton. Multimodal learning with transformers: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10): 12113–12132, 2023. Ping Yang, Junjie Wang, Ruyi Gan, Xinyu Zhu, Lin Zhang, Ziwei Wu, Xinyu Gao, Jiaxing Zhang, and Tetsuya Sakai. Zero-shot learners for natural language understanding via a unified multiple choice perspective. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7042–7055, Abu Dhabi, United Arab Emirates, December 2022a. Association for Computational Linguistics. URL https://aclanthology.org/2022.emnlp-main.474. Xiangli Yang, Zixing Song, Irwin King, and Zenglin Xu. A survey on deep semisupervised learning. CoRR, abs/2103.00550, 2021. URL https://arxiv.org/abs/ 2103.00550. Zhengyuan Yang, Zhe Gan, Jianfeng Wang, Xiaowei Hu, Yumao Lu, Zicheng Liu, and Lijuan Wang. An empirical study of gpt-3 for few-shot knowledge-based vqa. In Proceedings of the AAAI conference on artificial intelligence, volume 36, pages 3081–3089, 2022b. Shengyu Zhang, Linfeng Dong, Xiaoya Li, Sen Zhang, Xiaofei Sun, Shuhe Wang, Jiwei Li, Runyi Hu, Tianwei Zhang, Fei Wu, et al. Instruction tuning for large language models: A survey. arXiv preprint arXiv:2308.10792, 2023a. Xiang Zhang, Junbo Zhao, and Yann LeCun. Character-level convolutional networks for text classification. In C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc., 2015. URL https://proceedings.neurips.cc/paper_files/paper/2015/file/250cf8b51c773f3f8dc8b4be867a9a02-Paper.pdf. Yifan Zhang, Bingyi Kang, Bryan Hooi, Shuicheng Yan, and Jiashi Feng. Deep long-tailed learning: A survey. IEEE transactions on pattern analysis and machine intelligence, 45(9):10795–10816, 2023b. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, et al. A survey of large language models. arXiv preprint arXiv:2303.18223, 2023. Yukun Zhu, Ryan Kiros, Richard S. Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. Aligning books and movies: Towards story-like visual explanations by watching movies and reading books. CoRR, abs/1506.06724, 2015. URL http://arxiv.org/abs/1506.06724. Yang Zou, Zhiding Yu, B.V.K. Vijaya Kumar, and Jinsong Wang. Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In Proceedings of the European Conference on Computer Vision (ECCV), September 2018. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/101135 | - |
| dc.description.abstract | 本研究針對零樣本主題分類（Zero-Shot Topic Classification, ZSTC）問題，提出一種結合維基百科知識與自訓練技術的WC-SBERT 模型。相較於傳統監督式學習方法，ZSTC 旨在無需任何已標註訓練數據的前提下，將文本劃分至預定義主題類別。此能力對於處理數據稀缺、主題多樣且標註成本高昂的實際應用場景至關重要。
WC-SBERT 模型首先利用維基百科資料進行預訓練，獲取廣泛語義知識；隨後透過自訓練技術強化分類能力，將預訓練知識遷移至特定主題分類任務。於多個基準數據集（AG News、Yahoo Answers、DBpedia）的評估結果顯示，該模型不僅優於傳統SBERT 模型，更在AG News 與Yahoo Answers 數據集達到最先進（SOTA）水準。 除了提出新模型，本研究亦探討描述性標籤增強（Descriptive Label Augmentation）與自動提示工程（Auto Prompt Engineering, APE）技術，證實透過GPT 模型生成富含語義信息的標籤描述，可顯著提升分類效能。 另一核心貢獻在於針對大型語言模型（LLM）在ZSTC 任務中的表現，進行系統性的基準測試與比較分析。實驗揭示了LLM 與BERT-based 模型在不同情境下的優劣勢：儘管LLM 展現強大泛化能力，但在特定領域與資源受限情境下，經過優化的WC-SBERT 仍具備高度競爭力與效率優勢。 綜上所述，本研究驗證了WC-SBERT 模型有效性，並提供BERT-based 模型與LLM 在零樣本分類任務的完整比較基準，為該領域研究提供具價值的參考依據。 | zh_TW |
| dc.description.abstract | This research addresses Zero-Shot Topic Classification (ZSTC) by proposing WCSBERT, a model integrating Wikipedia knowledge with self-training techniques. Unlike traditional supervised learning, ZSTC categorizes text into predefined topics without labeled training data, a capability essential for scenarios with data scarcity and high annotation costs.
WC-SBERT leverages Wikipedia for pre-training to acquire broad semantic knowledge, followed by self-training to transfer this knowledge to specific classification tasks. Evaluations on benchmark datasets (AG News, Yahoo Answers, DBpedia) show that WCSBERT consistently outperforms traditional SBERT and achieves state-of-the-art (SOTA) results on AG News and Yahoo Answers. Additionally, this study explores Descriptive Label Augmentation and Auto Prompt Engineering (APE), confirming that semantically rich label descriptions generated via GPT models significantly enhance classification performance. Another core contribution is a systematic benchmarking of Large Language Models (LLMs) in ZSTC. Results reveal the trade-offs between LLMs and BERT-based models: while LLMs show strong generalization, the optimized WC-SBERT remains highly competitive and efficient in domain-specific and resource-constrained environments. Overall, this study validates WC-SBERT and establishes a comprehensive benchmark comparing BERT-based models and LLMs, providing a valuable reference for the field. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-12-31T16:04:08Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-12-31T16:04:08Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員會審定書（Verification Letter from the Oral Examination Committee） i
Acknowledgements iii 摘要 v Abstract vii Contents ix List of Figures xv List of Tables xvii Chapter 1 Introduction 1 Chapter 2 Related Work 5 2.1 Transformer architecture 5 2.1.1 BERT 5 2.1.2 SBERT 6 2.1.3 LLM 7 2.1.4 LLM Quantization 9 2.2 Text classification 11 2.2.1 Zero-shot topic classification 13 2.3 Self-training 14 2.4 Use of Wikipedia Data in Open-domain Zero-shot Classification 16 Chapter 3 Proposed Approach 19 3.1 Stage 1: Pre-training 22 3.2 Stage 2: Self-Training 24 3.2.1 Preprocessing and Definition of Key Components 24 3.2.2 Self-Training Workflow 25 3.2.3 Key Changes from Previous WC-SBERT Self-Training Approaches 26 3.2.4 Mathematical Formulation of Training Triplets 27 Chapter 4 Datasets 29 4.1 Training dataset 29 4.2 Target datasets for zero-shot evaluation 30 Chapter 5 Experiments 33 5.1 Supervised Baselines 33 5.1.1 SBERT (Triplet Loss) + 1NN 33 5.1.2 Results and Comparison 34 5.1.3 Analysis and Discussion 34 5.2 WC-SBERT Pre-trained Model 35 5.2.1 Training Configuration and Parameters 36 5.2.2 Evaluation Methodology 36 5.2.2.1 Evaluation Sample Generation 37 5.2.2.2 Evaluation Metrics and Tools 38 5.2.3 Performance Evaluation and Analysis 39 5.2.4 Data Distribution Analysis and Category Pruning Experiment 39 5.2.4.1 Long-tail Mitigation Results 41 5.2.4.2 Embedding stability Analysis 42 5.2.4.3 Downstream Task Validation 43 5.2.4.4 Summary 44 5.2.5 Ablation Study on Pre-training Design 45 5.2.5.1 Discussion on Pre-training Contributions 46 5.3 Descriptive Label Augmentation Experiment 47 5.3.1 Motivation and Objective 47 5.3.2 Label Augmentation Design 48 5.3.3 Experimental Setup 48 5.3.4 Results 48 5.3.5 Confusion Matrix Analysis 49 5.3.6 GPT-based Descriptive Label Augmentation 51 5.3.6.1 AGNEWS Descriptive Labels 52 5.3.6.2 Experimental Results 52 5.3.6.3 Analysis and Discussion 53 5.4 Auto Prompt Engineering Approach 53 5.4.1 Two-Stage Structure of AutoPrompt 54 5.4.2 Ranking Stage 54 5.4.3 Generation Stage 56 5.4.3.1 Label Generation Process for AGNEWS Dataset 58 5.4.3.2 Experimental Results 60 5.4.3.3 Analysis and Discussion 60 5.5 Self-Training Experiment 61 5.5.1 Self-Training Methodology 62 5.5.1.1 Inference Step: Constructing the Training Dataset 62 5.5.1.2 Finetune Step: Adapting the Model to the Target Dataset 64 5.5.2 Experimental Results 65 5.6 LLM Experiments 65 5.6.1 Quantization Parameters 66 5.7 Experimental Setup 68 5.7.1 Prompt Design 68 5.7.1.1 Zero-shot Prompt 68 5.7.1.2 Few-shot Prompt Setting 70 5.7.2 Inference Phase 71 5.7.2.1 Format Control 72 5.7.2.2 Temperature Adjustment 73 5.7.3 Experimental Results 73 5.7.4 Analysis and Discussion 75 5.7.4.1 Comparison of Few-shot vs. Zero-shot Prompt Setting 75 5.7.4.2 Comparison of WC-SBERT and LLMs 76 5.7.4.3 Model-specific Observations 77 5.8 Experimental Analysis and Comparison 77 5.8.1 Comparison of WC-SBERT and Mainstream Models 77 Chapter 6 Conclusions and Future Work 79 6.1 Conclusions 79 6.2 Future Work 80 References 83 Appendix A — Descriptive Label Augmentation Experiment Details 93 A.1 GPT-based Descriptive Label Augmentation Experiment Details 93 A.1.1 Instruction for GPT-based Descriptive Label Augmentation 93 A.1.2 Generated Descriptive Labels 95 A.1.2.1 Yahoo Answers Descriptive Labels 96 A.1.2.2 DBpedia Descriptive Labels 96 A.2 AutoPrompt Generation Experiment Details 96 A.2.1 Step Prompt for AutoPrompt Generation Stage 96 Appendix B — LLM Experiment Details 99 B.1 Zero-shot and Few-shot Prompt Design 99 B.1.1 Yahoo Answers Zero-shot Prompt Design 99 B.1.2 Yahoo Answers Few-shot Prompt Design 100 B.1.3 DBpedia Zero-shot Prompt Design 103 B.1.4 DBpedia Few-shot Prompt Design 104 | - |
| dc.language.iso | en | - |
| dc.subject | 零樣本訓練主題分類 | - |
| dc.subject | SBERT | - |
| dc.subject | 維基百科 | - |
| dc.subject | 自訓練 | - |
| dc.subject | 對比學習 | - |
| dc.subject | 知識圖譜 | - |
| dc.subject | 大型語言模型 | - |
| dc.subject | Zero-shot topic classification | - |
| dc.subject | SBERT | - |
| dc.subject | Wikipedia | - |
| dc.subject | Self-training | - |
| dc.subject | Contrastive learning | - |
| dc.subject | Knowledge graph | - |
| dc.subject | LLM | - |
| dc.title | 零樣本主題分類的進展：基於 BERT 模型與大型語言模型的比較與分析 | zh_TW |
| dc.title | Advancing Zero-Shot Topic Classification: A Comparative Study of BERT-based Models and Large Language Models | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 114-1 | - |
| dc.description.degree | 博士 | - |
| dc.contributor.coadvisor | 張智星 | zh_TW |
| dc.contributor.coadvisor | Jyh-Shing Jang | en |
| dc.contributor.oralexamcommittee | 張俊盛;古倫維;鄭卜壬;曾元顯 | zh_TW |
| dc.contributor.oralexamcommittee | Chun-Sheng Chang;Lun-Wei Ku;Pu-Jen Cheng;Yuen-Hsien Tseng | en |
| dc.subject.keyword | 零樣本訓練主題分類,SBERT維基百科自訓練對比學習知識圖譜大型語言模型 | zh_TW |
| dc.subject.keyword | Zero-shot topic classification,SBERTWikipediaSelf-trainingContrastive learningKnowledge graphLLM | en |
| dc.relation.page | 107 | - |
| dc.identifier.doi | 10.6342/NTU202504846 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2025-12-30 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| dc.date.embargo-lift | 2026-01-01 | - |
| 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-114-1.pdf | 2.19 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。