華語--印尼語機器翻譯

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：22

、訪客IP：3.145.216.39

姓名

穆何曼(Muhammad Fhadli) 查詢紙本館藏

畢業系所

資訊工程學系

論文名稱

華語--印尼語機器翻譯
(Chinese-Indonesian Low-Resource Neural Machine Translation)

相關論文

★ A Real-time Embedding Increasing for Session-based Recommendation with Graph Neural Networks	★ 基於主診斷的訓練目標修改用於出院病摘之十代國際疾病分類任務
★ 混合式心臟疾病危險因子與其病程辨識於電子病歷之研究	★ 基於 PowerDesigner 規範需求分析產出之快速導入方法
★ 社群論壇之問題檢索	★ 非監督式歷史文本事件類型識別──以《明實錄》中之衛所事件為例
★ 應用自然語言處理技術分析文學小說角色之關係：以互動視覺化呈現	★ 基於生醫文本擷取功能性層級之生物學表徵語言敘述：由主成分分析發想之K近鄰算法
★ 基於分類系統建立文章表示向量應用於跨語言線上百科連結	★ Code-Mixing Language Model for Sentiment Analysis in Code-Mixing Data
★ 藉由加入多重語音辨識結果來改善對話狀態追蹤	★ 對話系統應用於中文線上客服助理:以電信領域為例
★ 應用遞歸神經網路於適當的時機回答問題	★ 使用多任務學習改善使用者意圖分類
★ 使用轉移學習來改進針對命名實體音譯的樞軸語言方法	★ 基於歷史資訊向量與主題專精程度向量應用於尋找社群問答網站中專家

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

[檢視]

[下載]

本電子論文使用權限為同意立即開放。
已達開放權限電子全文僅授權使用者為學術研究之目的，進行個人非營利性質之檢索、閱讀、列印。
請遵守中華民國著作權法之相關規定，切勿任意重製、散佈、改作、轉貼、播送，以免觸法。

摘要(中)

從低資源數據中構建一個好的機器翻譯器是最近的挑戰之一。為了解決這個問題，出現了轉移學習並為此問題提供了解決方案。機器翻譯器的另一個重要問題是構建沒有平行語料庫資源的良好機器翻譯器。該問題的解決方案之一是使用師生框架來生成生成並行語料庫的源-目標機器。在本文中，我們試圖利用機器生成的語料庫來解決構建低資源機器翻譯的問題。基本上，我們結合解決低資源和零資源機器翻譯問題的解決方案來解決資源機器翻譯本身的問題。我們的想法是生成大量機器生成的數據，我們可以將這些數據用於培訓，然後使用轉移學習繼續使用低資源數據進行培訓。我們在本論文中的貢獻證明，機器生成的數據可以幫助我們培訓低資源的人為數據。據我們所知，由於數據稀缺問題，之前沒有討論中印機器翻譯的論文。因此，我們以英語為中心進行中印機器翻譯，並利用一些馬來西亞語料庫。

摘要(英)

Build a good machine translator out of low resource data is one of the challenges recently. In order to tackle this issue, transfer learning came up and bring a solution to this problem. Another substantial problem for machine translator is to build the good machine translator with no resource of parallel corpus available. One of the solutions for this problem is to use the teacher-student framework to produce a source-target machine-generated parallel corpus.In this thesis, we tried to tackle the problem of building low resource machine translatorby utilizing machine-generated corpus. Basically, we combinethe solution for tackling low resource and zero resource machine translation problem to address the problem of low resource machine translation itself. The idea is to produce huge machine-generated data that we can use for training and then use transfer learning to continue the training with low resource data.Our contribution in this thesis is proved that machine-generated data can help us to train low resource human-generated data. As far as we know, there is no previous paper that discusses Chinese-Indonesian machine translation because of the data scarcity problem. Therefore, we do Chinese-Indonesian machine translation with English as a pivot and utilize some of the Malaysian corpora.

關鍵字(中)

★ 中文
★ 印度尼西亞語
★ 機器翻譯
★ 師生框架
★ 轉學習

關鍵字(英)

★ Chinese
★ Indonesian
★ Machine Translation
★ Teacher-StudentFramework
★ Transfer Learning

論文目次

摘要
................................................................................................................................................viABSTRACT..................................................................................................................................viiACKNOWLEDGEMENT...........................................................................................................viiiCONTENTS...................................................................................................................................ixLIST OF FIGURES........................................................................................................................xiLIST OF TABLES........................................................................................................................xii1.Introduction..............................................................................................................................11.1.Motivation.........................................................................................................................11.2.Problem Description.........................................................................................................51.3.Thesis Organization..........................................................................................................62.Related Work...........................................................................................................................72.1.Chinese Indonesia Machine Translation...........................................................................72.2.Low Resource Machine Translation.................................................................................82.3.Evaluation of Machine Translation...................................................................................92.4.Tools for Machine Translation..........................................................................................93.Methodology..........................................................................................................................123.1.Formal Problem Definition.............................................................................................123.2.System Flow....................................................................................................................12
x4.Experiment.............................................................................................................................154.1.Datasets...........................................................................................................................154.2.Experimental Settings.....................................................................................................204.3.Evaluation.......................................................................................................................204.4.Experimental Results......................................................................................................215.Discussion..............................................................................................................................275.1.Performance of Teacher Model......................................................................................275.2.Student Model and Transfer Learning............................................................................286.Conclusion.............................................................................................................................43References.....................................................................................................................................44

參考文獻

[1]M. Aadil andM. Asger, “An Overview of Statistical Machine Translation Tools,” Int. J. Adv. Res. Comput. Sci. Softw. Eng., vol. 7, no. 7, p. 289, 2017.[2]D. Bahdanau, K. Cho, and Y. Bengio, “Neural Machine Translation by Jointly Learning to Align and Translate,” pp. 1–15, 2014.[3]P. F. Brown et al., “a Statistical Approach To Machine Translation,” vol. 16, no. 2, pp. 79–85, 1990.[4]B. Zoph, D. Yuret, J. May, and K. Knight, “Transfer Learning for Low-Resource Neural Machine Translation,” 2016.[5]J. Gu, H. Hassan, J. Devlin, and V. O. K. Li, “Universal Neural Machine Translation for Extremely Low Resource Languages,” pp. 344–354, 2018.[6]S. H. Ramesh and K. P. Sankaranarayanan, “Neural Machine Translation for Low Resource Languages using BilingualLexicon Induced from Comparable Corpora,” pp. 112–119, 2018.[7]Y. Cheng, Y. Liu, Q. Yang, M. Sun, and W. Xu, “Neural Machine Translation with Pivot Languages,” 2016.[8]Y. Chen, Y. Liu, Y. Cheng, and V. O. K. Li, “A Teacher-Student Framework for Zero-Resource Neural Machine Translation,” 2017.[9]H. Nakayama and N. Nishida, “Zero-resource machine translation by multimodal encoder–decoder network with multimedia pivot,” Mach. Transl., vol. 31, no. 1–2, pp. 49–64, 2017.
45[10]A. Booth, “China ’ s EconomicRelations with Indonesia :,” J. Curr. Southeast Asian Aff., vol. 30, no. 2, pp. 141–160, 2011.[11]A. Vaswani et al., “Attention Is All You Need,” no. Nips, 2017.[12]Papineni Kishore, R. Salim, W. Todd, and Z. Wei-Jing, “BLEU: a Method for Automatic Evaluation of Machine Translation,” Des. Rev. challenging urban aesthetic Control, no. July, p. 219, 1994.[13]J. Tiedemann, “Parallel Data, Tools and Interfaces in OPUS,” Proc. Lr. 2012, pp. 2214–2218, 2012.[14]G. Klein, Y. Kim, Y. Deng, V. Nguyen, J. Senellart, and A. M. Rush, “OpenNMT: Neural Machine Translation Toolkit,” pp. 67–72, 2018

指導教授

蔡宗翰(Tzong-Han Tsai)

審核日期

2019-7-25

推文