1. NCCU Academic Hub
  2. 學術產出
  3. College of Informatics
  4. Theses
  5. Item

學術產出-Theses

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

  • No doi shows Citation Infomation
題名 以範例為基礎之英漢TIMSS詴題輔助翻譯
Using Example-based Translation Techniques for Computer Assisted Translation of TIMSS Test Items
作者 張智傑
Chang, Chih Chieh
貢獻者 劉昭麟
Liu, Chao Lin
張智傑
Chang, Chih Chieh
關鍵詞 自然語言處理
試題翻譯
機器翻譯
Natural language processing
Item translation
Machine translation
TIMSS
日期 2008
上傳時間 17-Sep-2009 14:04:36 (UTC+8)
摘要 本論文應用以範例為基礎的機器翻譯技術，應用英漢雙語對應的結構輔助英漢單句語料的翻譯。翻譯範例是運用一種特殊的結構，此結構包含來源句的剖析樹、目標句的字串、以及目標句和來源句詞彙對應關係。將翻譯範例建立資料庫，以提供來源句作詞序交換的依據，接著透過字典翻譯，以及利用統計式中英詞彙對列和語言模型來選詞，最後填補缺少的量詞，產生建議的翻譯。我們是以2003年國際數學與科學教育成就趨勢調查測驗詴題為主要翻譯的對象，以期提升翻譯的一致性和效率。以NIST 和BLEU 的評比方式，來評估和比較Google Translate 和Yahoo!線上翻譯系統及本系統所達成的翻譯品質。我們的系統經過詞序調動以及填補量詞後，翻譯品質比我們前一代系統要佳，但整體效果沒有比Google Translate 和Yahoo!線上翻譯的品質要佳。
This paper presents an example-based machine translation based on bilingual structured string tree correspondence (BSSTC). The BSSTC structure includes a parse tree in source language, a string in target language and the correspondence between the source language tree and the target language string.

We designed an English to Chinese computer assisted translation system for Trends in International Mathematics and Science Study (TIMSS), through the BSSTC structure reordering, directory translation, choosing translation statistics model and measure word generation.
We evaluated our system by the BLEU and NIST score and compared with Google Translate and Yahoo! Translate. By reordering selected word sequences and inserting measure words in the default translations, the current system achieved a higher quality of default translations than the previous implementation of our research group, but the overall effects still lag behind that achieved by Google and Yahoo!.
參考文獻 [1] 中研院中文剖析器檢索系統，http://parser.iis.sinica.edu.tw/ [Accessed: Oct. 28, 2008].
[2] 中研院平衡語料庫詞類標記集，http://ckipsvr.iis.sinica.edu.tw/category_list.doc [Accessed: Oct. 28, 2008].
[3] 自由時報中英對照讀新聞，http://www.libertytimes.com.tw/2008/new/jan/15/english.htm [Accessed: Jun. 30, 2008].
[4] 呂明欣，電腦輔助詴題翻譯：以國際數學與科學教育成就趨勢調查為例，國立政治大學資訊科學所，碩士論文，2007。
[5] 夏敏翔、張耀升和盧文祥，使用流暢性改善詞組翻譯的統計式機器翻譯，第十八屆自然語言與語音處理研討會論文集。台灣，新竹，2006。
[6] 教育部委託宜蘭縣發展九年一貫課程建置語文學習領域（英語）國中教科書補充資料暨題庫建置計畫，http://140.111.66.37/english/ [Accessed: Oct. 28, 2008].
[7] M. H. Al-Adhaileh, T. E. Kong and Y. Zaharin, “A synchronization structure of SSTC and its applications in machine translation”, Proceedings of the International Conference on Computational Linguistics -2002 Post-Conference Workshop on Machine Translation in Asia, 1–8, 2002.
[8] C. Boitet and Y. Zaharin, “Representation trees and string-tree correspondences”, Proceedings of the Twelfth International Conference on Computational Linguistics, 59–64, 1998.
[9] P. F. Brown, J. Cocke, S. A. D. Pietra, V. J. D. Pietra, F. Jelinek, J. D. Lafferty, R. L. Mercer and P. S. Roossin, “A Statistical Approach to Machine Translation”, Computational Linguistics, 79-85, 1990.
[10] Concise Oxford English Dictionary, http://stardict.sourceforge.net/Dictionaries_zh_TW.php [Accessed: Oct. 28, 2008].
58
[11] G. Doddington, “Automatic evaluation of machine translation quality using n-gram co-occurrence statistics”, Proceedings of the Second International Conference of Human Language Technology Research, 138–145, 2002.
[12] B. J. Dorr, P. W. Jordan and J. W. Benoit, “A Survey of Current Paradigms in Machine Translation” Advances in Computers, London: Academic Press, 1–68, 1999.
[13] Google Translate, http://translate.google.com/translate_t [Accessed: Oct. 28, 2008].
[14] D. Klein and C. Manning, “Accurate Unlexicalized Parsing”, Proceedings of the Forty-first Meeting of the Association for Computational Linguistics, 423–430, 2003.
[15] K. Knight and S. K. Luk, “Building a large-scale knowledge base for machine translation”, Proceedings of the Twelfth National Conference on Artificial intelligence, 773–778, 1994.
[16] P. Koehn, F. J. Och and D. Marcu, “Statistical phrase-based translation”, Proceedings of the Human Language Technology Conference, 127–133, 2003.
[17] R. Levy and C. Manning, “Is it harder to parse Chinese, or the Chinese Treebank?” Proceedings of the Forty-first Conference of the Association for Computational Linguistics, 439–446, 2003.
[18] Z. Liu, H. Wang and H. Wu, “Example-based Machine Translation Based on TSC and Statistical Generation”, Proceedings of the Tenth Machine Translation Summit, 25–32, 2005.
[19] F. J. Och, “An Efficient Method for Determining Bilingual Word Classes”, Proceedings of European Chapter of the Association for Computational Linguistics, 71–76, 1999.
[20] F. J. Och and H. Ney, “Improved Statistical Alignment Models”, Proceedings of the Thirty-eighth Annual Meeting of the Association for Computational Linguistics, 440–447, 2000.
59
[21] K. Papineni, S. Roukos, T. Ward, and W. J. Zhu, “Bleu: a method for automatic evaluation of machine translation”, Proceedings of the Fortieth Annual Meeting of the Association for Computational Linguistics, 311–318, 2002.
[22] The Stanford Parser: A statistical parser, http://nlp.stanford.edu/software/ [Accessed: Oct. 28, 2008].
[23] A. Stolcke, SRILM – an extensible language modeling toolkit. Proceedings of the intelligence Conference on Spoken Language Processing, 901–904, 2002. http://www.speech.sri.com/projects/srilm/ [Accessed: Oct. 28, 2008].
[24] S. Sato and M. Nagao, Toward Memory-Based Translation”, Proceedings of International Conference on Computational Linguistics, 247–252, 1990.
[25] The International Association for the Evaluation of Education Achievement, http://www.iea.nl/ [Accessed: Oct. 28, 2008].
[26] TIMSS 中文版官方網頁, http://timss.sec.ntnu.edu.tw/timss2007/news.asp [Accessed: Oct. 28, 2008].
[27] The Porter Stemming Algorithm, http://www.tartarus.org/martin/PorterStemmer/ [Accessed: Oct. 28, 2008].
[28] WordNet API, http://nlp.stanford.edu/nlp/javadoc/wn/ [Accessed: Oct. 28, 2008].
[29] F. Wong, M. Dong and D. Hu, Machine Translation Based on Translation Corresponding Tree Structure, Tsinghua Science & Technology, 25–31, 2006.
[30] YAHOO! 雅虎線上翻譯, http://tw.babelfish.yahoo.com/ [Accessed: Oct. 28, 2008].
[31] D. Zhang, M. Li, N. Duan, C. H. Li and M. Zhou, “Measure Word Generation for English-Chinese SMT Systems”, Proceedings of Association for Computational Linguistics, 89–96, 2008.
描述 碩士
國立政治大學
資訊科學學系
95753012
97
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0095753012
資料類型 thesis
dc.contributor.advisor 劉昭麟zh_TW
dc.contributor.advisor Liu, Chao Linen_US
dc.contributor.author (Authors) 張智傑zh_TW
dc.contributor.author (Authors) Chang, Chih Chiehen_US
dc.creator (作者) 張智傑zh_TW
dc.creator (作者) Chang, Chih Chiehen_US
dc.date (日期) 2008en_US
dc.date.accessioned 17-Sep-2009 14:04:36 (UTC+8)-
dc.date.available 17-Sep-2009 14:04:36 (UTC+8)-
dc.date.issued (上傳時間) 17-Sep-2009 14:04:36 (UTC+8)-
dc.identifier (Other Identifiers) G0095753012en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/32695-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學學系zh_TW
dc.description (描述) 95753012zh_TW
dc.description (描述) 97zh_TW
dc.description.abstract (摘要) 本論文應用以範例為基礎的機器翻譯技術，應用英漢雙語對應的結構輔助英漢單句語料的翻譯。翻譯範例是運用一種特殊的結構，此結構包含來源句的剖析樹、目標句的字串、以及目標句和來源句詞彙對應關係。將翻譯範例建立資料庫，以提供來源句作詞序交換的依據，接著透過字典翻譯，以及利用統計式中英詞彙對列和語言模型來選詞，最後填補缺少的量詞，產生建議的翻譯。我們是以2003年國際數學與科學教育成就趨勢調查測驗詴題為主要翻譯的對象，以期提升翻譯的一致性和效率。以NIST 和BLEU 的評比方式，來評估和比較Google Translate 和Yahoo!線上翻譯系統及本系統所達成的翻譯品質。我們的系統經過詞序調動以及填補量詞後，翻譯品質比我們前一代系統要佳，但整體效果沒有比Google Translate 和Yahoo!線上翻譯的品質要佳。zh_TW
dc.description.abstract (摘要) This paper presents an example-based machine translation based on bilingual structured string tree correspondence (BSSTC). The BSSTC structure includes a parse tree in source language, a string in target language and the correspondence between the source language tree and the target language string.

We designed an English to Chinese computer assisted translation system for Trends in International Mathematics and Science Study (TIMSS), through the BSSTC structure reordering, directory translation, choosing translation statistics model and measure word generation.
We evaluated our system by the BLEU and NIST score and compared with Google Translate and Yahoo! Translate. By reordering selected word sequences and inserting measure words in the default translations, the current system achieved a higher quality of default translations than the previous implementation of our research group, but the overall effects still lag behind that achieved by Google and Yahoo!.		en_US
dc.description.tableofcontents 第一章 緒論 .......................................................................................................................... 1
1.1 研究背景與動機 .................................................................................................... 1
1.2 研究方法 ................................................................................................................ 3
1.3 論文架構 ................................................................................................................ 4
第二章 文獻回顧 .................................................................................................................. 5
2.1 機器翻譯 ................................................................................................................ 5
2.2 增加翻譯流暢性 .................................................................................................... 8
第三章 系統相關技術 .......................................................................................................... 9
3.1 詞序交換技術 ...................................................................................................... 10
3.1.1 雙語樹對應字串的結構(BSSTC) ........................................................... 10
3.1.2 建立BSSTC結構和產生範例樹 ............................................................ 13
3.1.3 搜尋相同範例樹 ...................................................................................... 16
3.2 翻譯處理 .............................................................................................................. 21
3.3 調整翻譯選詞方法 .............................................................................................. 23
3.4 填補量詞技術 ...................................................................................................... 25
3.4.1 中文量詞分析 .......................................................................................... 26
3.4.2 填補量詞方法 .......................................................................................... 29
第四章 系統效率評估 ........................................................................................................ 32
4.1 實驗來源 .............................................................................................................. 32
4.2 實驗設計 .............................................................................................................. 34
4.3 BLEU及NIST指標評估 .................................................................................... 39
4.4 實驗結果與分析 .................................................................................................. 41
4.4.1 不同規則詞典檔作比較 .......................................................................... 41
4.4.2 不同選詞模型語料之比較 ...................................................................... 44
4.4.3 不同範例樹語料之比較 .......................................................................... 45
4.4.4 不同系統以及年級之比較 ...................................................................... 48
4.4.5 產生量詞後之比較 .................................................................................. 50
4.4.6 TIMSS2003實驗組在不同系統之比較 ................................................. 52
第五章 結論與未來展望 .................................................................................................... 54
參考文獻 .............................................................................................................................. 57
附錄Ⅰ 中研院平衡語料庫詞類標記 ................................................................................ 60
附錄Ⅱ Penn Treebank Tags ............................................................................................... 61
附錄Ⅲ NIST及BLEU分數 .............................................................................................. 63		zh_TW
dc.format.extent 275759 bytes-
dc.format.extent 117304 bytes-
dc.format.extent 232255 bytes-
dc.format.extent 403572 bytes-
dc.format.extent 308007 bytes-
dc.format.extent 319565 bytes-
dc.format.extent 1103907 bytes-
dc.format.extent 925201 bytes-
dc.format.extent 346921 bytes-
dc.format.extent 368394 bytes-
dc.format.extent 5466160 bytes-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0095753012en_US
dc.subject (關鍵詞) 自然語言處理zh_TW
dc.subject (關鍵詞) 試題翻譯zh_TW
dc.subject (關鍵詞) 機器翻譯zh_TW
dc.subject (關鍵詞) Natural language processingen_US
dc.subject (關鍵詞) Item translationen_US
dc.subject (關鍵詞) Machine translationen_US
dc.subject (關鍵詞) TIMSSen_US
dc.title (題名) 以範例為基礎之英漢TIMSS詴題輔助翻譯zh_TW
dc.title (題名) Using Example-based Translation Techniques for Computer Assisted Translation of TIMSS Test Itemsen_US
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) [1] 中研院中文剖析器檢索系統，http://parser.iis.sinica.edu.tw/ [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) [2] 中研院平衡語料庫詞類標記集，http://ckipsvr.iis.sinica.edu.tw/category_list.doc [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) [3] 自由時報中英對照讀新聞，http://www.libertytimes.com.tw/2008/new/jan/15/english.htm [Accessed: Jun. 30, 2008].zh_TW
dc.relation.reference (參考文獻) [4] 呂明欣，電腦輔助詴題翻譯：以國際數學與科學教育成就趨勢調查為例，國立政治大學資訊科學所，碩士論文，2007。zh_TW
dc.relation.reference (參考文獻) [5] 夏敏翔、張耀升和盧文祥，使用流暢性改善詞組翻譯的統計式機器翻譯，第十八屆自然語言與語音處理研討會論文集。台灣，新竹，2006。zh_TW
dc.relation.reference (參考文獻) [6] 教育部委託宜蘭縣發展九年一貫課程建置語文學習領域（英語）國中教科書補充資料暨題庫建置計畫，http://140.111.66.37/english/ [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) [7] M. H. Al-Adhaileh, T. E. Kong and Y. Zaharin, “A synchronization structure of SSTC and its applications in machine translation”, Proceedings of the International Conference on Computational Linguistics -2002 Post-Conference Workshop on Machine Translation in Asia, 1–8, 2002.zh_TW
dc.relation.reference (參考文獻) [8] C. Boitet and Y. Zaharin, “Representation trees and string-tree correspondences”, Proceedings of the Twelfth International Conference on Computational Linguistics, 59–64, 1998.zh_TW
dc.relation.reference (參考文獻) [9] P. F. Brown, J. Cocke, S. A. D. Pietra, V. J. D. Pietra, F. Jelinek, J. D. Lafferty, R. L. Mercer and P. S. Roossin, “A Statistical Approach to Machine Translation”, Computational Linguistics, 79-85, 1990.zh_TW
dc.relation.reference (參考文獻) [10] Concise Oxford English Dictionary, http://stardict.sourceforge.net/Dictionaries_zh_TW.php [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) 58zh_TW
dc.relation.reference (參考文獻) [11] G. Doddington, “Automatic evaluation of machine translation quality using n-gram co-occurrence statistics”, Proceedings of the Second International Conference of Human Language Technology Research, 138–145, 2002.zh_TW
dc.relation.reference (參考文獻) [12] B. J. Dorr, P. W. Jordan and J. W. Benoit, “A Survey of Current Paradigms in Machine Translation” Advances in Computers, London: Academic Press, 1–68, 1999.zh_TW
dc.relation.reference (參考文獻) [13] Google Translate, http://translate.google.com/translate_t [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) [14] D. Klein and C. Manning, “Accurate Unlexicalized Parsing”, Proceedings of the Forty-first Meeting of the Association for Computational Linguistics, 423–430, 2003.zh_TW
dc.relation.reference (參考文獻) [15] K. Knight and S. K. Luk, “Building a large-scale knowledge base for machine translation”, Proceedings of the Twelfth National Conference on Artificial intelligence, 773–778, 1994.zh_TW
dc.relation.reference (參考文獻) [16] P. Koehn, F. J. Och and D. Marcu, “Statistical phrase-based translation”, Proceedings of the Human Language Technology Conference, 127–133, 2003.zh_TW
dc.relation.reference (參考文獻) [17] R. Levy and C. Manning, “Is it harder to parse Chinese, or the Chinese Treebank?” Proceedings of the Forty-first Conference of the Association for Computational Linguistics, 439–446, 2003.zh_TW
dc.relation.reference (參考文獻) [18] Z. Liu, H. Wang and H. Wu, “Example-based Machine Translation Based on TSC and Statistical Generation”, Proceedings of the Tenth Machine Translation Summit, 25–32, 2005.zh_TW
dc.relation.reference (參考文獻) [19] F. J. Och, “An Efficient Method for Determining Bilingual Word Classes”, Proceedings of European Chapter of the Association for Computational Linguistics, 71–76, 1999.zh_TW
dc.relation.reference (參考文獻) [20] F. J. Och and H. Ney, “Improved Statistical Alignment Models”, Proceedings of the Thirty-eighth Annual Meeting of the Association for Computational Linguistics, 440–447, 2000.zh_TW
dc.relation.reference (參考文獻) 59zh_TW
dc.relation.reference (參考文獻) [21] K. Papineni, S. Roukos, T. Ward, and W. J. Zhu, “Bleu: a method for automatic evaluation of machine translation”, Proceedings of the Fortieth Annual Meeting of the Association for Computational Linguistics, 311–318, 2002.zh_TW
dc.relation.reference (參考文獻) [22] The Stanford Parser: A statistical parser, http://nlp.stanford.edu/software/ [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) [23] A. Stolcke, SRILM – an extensible language modeling toolkit. Proceedings of the intelligence Conference on Spoken Language Processing, 901–904, 2002. http://www.speech.sri.com/projects/srilm/ [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) [24] S. Sato and M. Nagao, Toward Memory-Based Translation”, Proceedings of International Conference on Computational Linguistics, 247–252, 1990.zh_TW
dc.relation.reference (參考文獻) [25] The International Association for the Evaluation of Education Achievement, http://www.iea.nl/ [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) [26] TIMSS 中文版官方網頁, http://timss.sec.ntnu.edu.tw/timss2007/news.asp [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) [27] The Porter Stemming Algorithm, http://www.tartarus.org/martin/PorterStemmer/ [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) [28] WordNet API, http://nlp.stanford.edu/nlp/javadoc/wn/ [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) [29] F. Wong, M. Dong and D. Hu, Machine Translation Based on Translation Corresponding Tree Structure, Tsinghua Science & Technology, 25–31, 2006.zh_TW
dc.relation.reference (參考文獻) [30] YAHOO! 雅虎線上翻譯, http://tw.babelfish.yahoo.com/ [Accessed: Oct. 28, 2008].zh_TW
dc.relation.reference (參考文獻) [31] D. Zhang, M. Li, N. Duan, C. H. Li and M. Zhou, “Measure Word Generation for English-Chinese SMT Systems”, Proceedings of Association for Computational Linguistics, 89–96, 2008.zh_TW