請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70076完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 許永真(Yung-Jen Hsu) | |
| dc.contributor.author | Sheng-Wen Chiang | en |
| dc.contributor.author | 蔣盛文 | zh_TW |
| dc.date.accessioned | 2021-06-17T03:42:12Z | - |
| dc.date.available | 2019-02-23 | |
| dc.date.copyright | 2018-02-23 | |
| dc.date.issued | 2018 | |
| dc.date.submitted | 2018-02-06 | |
| dc.identifier.citation | [1] M. Banko, M. J. Cafarella, S. Soderland, M. Broadhead, and O. Etzioni. Open information extraction from the web. IJCAI, pages 2670–2676, 2007.
[2] M.BankoandO.Etzioni.The tradeoffs between open and traditional relation extraction. In Proceedings of ACL-08: HLT, pages 28–36. Association for Computational Linguistics, June 2008. [3] L. Del Corro and R. Gemulla. Clausie: Clause-based open information extraction. In Proceedings of the 22Nd International Conference on World Wide Web, WWW ’13, pages 355–366. ACM, 2013. [4] O. Etzioni, A. Fader, J. Christensen, S. Soderland, and M. Mausam. Open information extraction: The second generation. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI’11, pages 3–10. AAAI Press, 2011. [5] A. Fader, S. Soderland, and O. Etzioni. Identifying relations for open information extraction. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP ’11, pages 1535–1545. Association for Computational Linguistics, 2011. [6] M. Faruqui and S. Kumar. Multilingual open relation extraction using cross-lingual projection. In HLT-NAACL, pages 1351–1356. The Association for Computational Linguistics, 2015. [7] P. Gamallo and M. Garcia. Multilingual open information extraction. In F. Pereira, P. Machado, E. Costa, and A. Cardoso, editors, Progress in Artificial Intelligence, pages 711–722. Springer International Publishing, 2015. [8] D. Klein and C. D. Manning. Accurate unlexicalized parsing. In E. Hinrichs and D. Roth, editors, Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1, ACL ’03, pages 423–430. Association for Computational Linguistics, 2003. [9] Mausam, M. Schmitz, R. Bart, S. Soderland, and O. Etzioni. Open language learn- ing for information extraction. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL ’12, pages 523–534. Association for Computational Linguistics, 2012. [10] 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 on Association for Computational Linguistics, ACL ’02, pages 311–318. Association for Computational Linguistics, 2002. [11] M. F. Porter. Readings in information retrieval. chapter An Algorithm for Suffix Stripping, pages 313–316. Morgan Kaufmann Publishers Inc., 1997. [12] Y. Wu, M. Schuster, Z. Chen, Q. V. Le, M. Norouzi, W. Macherey, M. Krikun, Y. Cao, Q. Gao, K. Macherey, J. Klingner, A. Shah, M. Johnson, X. Liu, ukasz Kaiser, S. Gouws, Y. Kato, T. Kudo, H. Kazawa, K. Stevens, G. Kurian, N. Patil, W. Wang, C. Young, J. Smith, J. Riesa, A. Rudnick, O. Vinyals, G. Corrado, M. Hughes, and J. Dean. Google’s neural machine translation system: Bridging the gap between human and machine translation. CoRR, abs/1609.08144, 2016. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70076 | - |
| dc.description.abstract | 開放式關係抽取 (Open Relation Extraction Systems, ORE) 系統從句 子中找出關係對。與傳統關係抽取不同，「開放式」意指不事先制定 (pre-define) 欲抽取的關係種類。
現存的所有英文 ORE 系統的設計都與英文文法或詞性 (part-of- speech) 高度相關，因此不容易直接應用於別種語言。而對於目前非英 文 ORE 系統，大部分基於英文 ORE 系統提出的概念，適度的修改以 合乎其他語言，此方式往往需要重新訓練資料或甚至重新設計系統。 有鑑於此，本論文提出一套基於翻譯器 (translator) 的多語言 (multilingual) ORE 系統，TransMORE，能應用於任何能翻譯至英文的自 然語言。由於 TransMORE 使用了第三方的翻譯器與英文 ORE 系統， 隨著翻譯器或英文 ORE 系統的進步，TransMORE 能同時與之進步， 毋需重新設計或再訓練任何資料。 在本研究中，除了與先前作品比較外，我們也實驗了使用不同英 文 ORE 系統對產出的影響，同時展現 TransMORE 易於抽換第三方 ORE 系統的特性。 | zh_TW |
| dc.description.abstract | Open domain relation extraction (ORE) systems identify relation and arguments phrases in a sentence, without any pre-defined underlying schema.
Most English ORE systems, including current state-of-the-art system, can only extract relations from English because their methods highly rely on lingustic grammar and/or part-of-speech tagging. For non-English ORE systems, most of them use ideas from English ORE systems, and redesign the language-dependent rules to fit their target language. This thesis presents a new multilingual ORE system, TransMORE, which uses a novel method for extracting relations from multilingual corpus. TransMORE bases on a third-party translator and English ORE system. With better performance translator and/or English ORE system, TransMORE can have better result as well. In this work, besides compare with previous work, we also experiment on TransMORE within different English ORE systems. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T03:42:12Z (GMT). No. of bitstreams: 1 ntu-107-R04922038-1.pdf: 813581 bytes, checksum: 7a11f1496a07c57f109bb08cd8285541 (MD5) Previous issue date: 2018 | en |
| dc.description.tableofcontents | 誌謝 ii
摘要 iii Abstract iv 1 Introduction and Problem 1 1.1 Motivation ................................. 1 1.2 Problem Description ........................ 2 1.3 Terminology and Notation ................... 2 1.4 Proposed Solution .......................... 2 1.5 Input and Output ........................... 3 1.6 Thesis Organization ........................ 4 2 Related Work 5 2.1 RE and ORE ................................. 5 2.2 English ORE Systems ........................ 5 2.3 Multilingual ORE ........................... 6 3 Methodoloy 8 3.1 Framework .................................. 8 3.1.1 Reduce to EORE ......................... 9 3.1.2 Phrase Mapper .......................... 9 3.2 Walk-through Example ...................... 17 4 Experiments 19 4.1 Annotation ................................ 19 4.2 Dataset ................................... 20 4.3 Experimental Results ...................... 21 4.3.1 Chinese ............................... 21 4.3.2 French ................................ 22 4.3.3 Summation ............................. 23 4.4 Discussion ................................ 24 4.4.1 Loss .................................. 24 4.4.2 Framework ............................. 24 4.4.3 翻譯器 ................................ 25 4.4.4 實驗結果分析 .......................... 26 4.4.5 Chinese vs French ..................... 26 5 Conclusion 27 5.1 Summary of Contributions .................. 27 5.2 Future Work ............................... 27 Bibliography 28 | |
| dc.language.iso | zh-TW | |
| dc.subject | 開放式關係抽取 | zh_TW |
| dc.subject | 翻譯 | zh_TW |
| dc.subject | 多語言 | zh_TW |
| dc.subject | Translation | en |
| dc.subject | Open Relation Extraction | en |
| dc.subject | Multilingual | en |
| dc.title | TransMORE: 基於翻譯的多語言開放式關係抽取 | zh_TW |
| dc.title | TransMORE: Translation Based Multilingual Open Relation Extraction | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 106-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 馬偉雲(Wei-Yun Ma),鄭卜壬(Pu-Jen Cheng),劉昭麟(Chao-Lin Liu) | |
| dc.subject.keyword | 開放式關係抽取,翻譯,多語言, | zh_TW |
| dc.subject.keyword | Open Relation Extraction,Translation,Multilingual, | en |
| dc.relation.page | 29 | |
| dc.identifier.doi | 10.6342/NTU201800338 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2018-02-07 | |
| 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 | |
|---|---|---|---|
| ntu-107-1.pdf 未授權公開取用 | 794.51 kB | 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。