請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81056完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 李允中(Yun-Chung Li) | |
| dc.contributor.author | Ching-Chung Hsiao | en |
| dc.contributor.author | 蕭景忠 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:28:21Z | - |
| dc.date.available | 2021-09-02 | |
| dc.date.available | 2022-11-24T03:28:21Z | - |
| dc.date.copyright | 2021-09-02 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-08-23 | |
| dc.identifier.citation | google-10000-english. https://github.com/first20hours/ google-10000-english. JavaPoet. https://github.com/square/javapoet. Jenkins. https://jenkins.io/. LESK algorithm. https://www.c-sharpcorner.com/article/lesk-algorithm-in-python-to-remove-word-ambiguity/. Simlex-999. https://fh295.github.io/simlex.html. Spring framework. https://spring.io/projects/spring-framework. Word frequency list of american list. https://www.wordfrequency.info/files/entries.pdf. WordNet. https://wordnet.princeton.edu/. S. R. Bowman, G. Angeli, C. Potts, and C. D. Manning. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, 2015. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding, 2019. A. Guttman. R-trees: A dynamic index structure for spatial searching. In Proceed- ings of the 1984 ACM SIGMOD International Conference on Management of Data, SIGMOD ’84, page 47–57, New York, NY, USA, 1984. Association for Computing Machinery. M. H. Hsieh. Construct and bind user interface components. Master’s thesis, National Taiwan University, 2021. C. D. Manning, M. Surdeanu, J. Bauer, J. Finkel, S. J. Bethard, and D. McClosky. The Stanford CoreNLP natural language processing toolkit. In Association for Com- putational Linguistics (ACL) System Demonstrations, pages 55–60, 2014. T. Mikolov, K. Chen, G. Corrado, and J. Dean. Efficient estimation of word repre- sentations in vector space, 2013. C. Saedi, A. Branco, J. Ant ́onio Rodrigues, and J. Silva. WordNet embeddings. In Proceedings of The Third Workshop on Representation Learning for NLP, pages 122– 131, Melbourne, Australia, July 2018. Association for Computational Linguistics. M. Schuster and K. Paliwal. Bidirectional recurrent neural networks. IEEE Trans- actions on Signal Processing, 45(11):2673–2681, 1997. C. J. Yu. Construct service components from open source java projects. Master’s thesis, National Taiwan University, 2021. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81056 | - |
| dc.description.abstract | 在之前的研究中，已將許多 Java 的開放原始碼轉換為服務元件，並且已將這些服務元件的訊息記錄在資料庫當中。然而使用者是否能從資料庫中取得所需的服務元件是一問題。此外，為了比較服務元件是否滿足需求，如何測量服務元件之間的相似度是另一問題。 本研究將 WordNet 資料庫轉換為詞嵌入，再利用 R-Tree 的結構儲存這些詞嵌入，以便使用者快速地取得相似的服務元件。並設計了一個結合 BERT 及 LSTM 的語言模型，此模型可以用來測量服務元件名稱的相似性。本研究也利用現有的服務元件來產生更多的訓練資料，使模型適應服務元件名稱。為了使服務元件順利地完成資料庫存取，自動將已存在的資料庫建立在伺服器上並修改的方法將會在本研究中進行討論。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:28:21Z (GMT). No. of bitstreams: 1 U0001-2308202107013500.pdf: 4357584 bytes, checksum: cb5bd769ed91bb08f4df96bceadcee99 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 誌謝 ii 摘要 iii Abstracts iv List of Figures viii List of Tables x Chapter 1 Introduction 1 Chapter 2 Related Work 3 2.1 WordNet 3 2.2 R-Tree 3 2.3 BERT 4 2.4 BidirectionalLSTM 5 Chapter 3 Word Embedding 7 3.1 TrainingApproach 7 3.2 Evaluation 8 3.2.1 SimLex-999 9 3.2.2 Scoring 9 3.3 Improvement 9 3.3.1 AddingWords 10 3.3.2 AdjustingtheWeightofRelation 10 3.3.3 ComputingInverseinBlockForm 10 3.3.4 TrainingTool 11 3.4 Results 11 Chapter 4 Index Server 14 4.1 Architecture 14 4.1.1 Insert 16 4.1.2 Search 16 4.2 QueryResults 19 Chapter 5 Service Components Similarity Model 21 5.1 ModelDesign 21 5.2 DataGeneration 22 5.2.1 TransferintoService-Name-Liked 23 5.2.2 Generate from other Service Component Names 24 5.3 Results 27 Chapter 6 Database Creator 29 6.1 CreateExistingDatabase 29 6.2 ModifyingDatabase 30 6.2.1 RetrieveDBInfoServer 32 6.2.2 EntityInformationExtractor 32 6.2.3 EntityClassGenerator 32 6.3 Pipeline 34 Chapter 7 Conclusion 37 Bibliography 39 A Service Component Database 41 | |
| dc.language.iso | zh-TW | |
| dc.subject | 空間索引 | zh_TW |
| dc.subject | 詞嵌入 | zh_TW |
| dc.subject | 語意相似性 | zh_TW |
| dc.subject | 語言模型 | zh_TW |
| dc.subject | word embedding | en |
| dc.subject | spatial index | en |
| dc.subject | language model | en |
| dc.subject | semantic similarity | en |
| dc.title | 使用者介面元件與服務元件的配對 | zh_TW |
| dc.title | Matchmake User Interface Components with Service Components | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 李俊宏(Hsin-Tsai Liu),陳錫民(Chih-Yang Tseng),范姜永益,李文廷 | |
| dc.subject.keyword | 詞嵌入,語意相似性,語言模型,空間索引, | zh_TW |
| dc.subject.keyword | word embedding,semantic similarity,language model,spatial index, | en |
| dc.relation.page | 42 | |
| dc.identifier.doi | 10.6342/NTU202102606 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-08-24 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 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 | |
|---|---|---|---|
| U0001-2308202107013500.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 4.26 MB | Adobe PDF |
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。