跳到主要內容

臺灣博碩士論文加值系統

(44.200.194.255) 您好!臺灣時間:2024/07/19 04:55
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:張鈺玫
研究生(外文):Yu Mei Chang
論文名稱:使用多種鑑別式模型以及特徵資訊於語音文件摘要之研究
論文名稱(外文):Exploiting Various Discriminative Models and Information Cues for Spoken Document Summarization
指導教授:陳柏琳陳柏琳引用關係
指導教授(外文):Chen, Berlin
學位類別:碩士
校院名稱:國立臺灣師範大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2010
畢業學年度:98
語文別:中文
論文頁數:133
中文關鍵詞:語音文件摘錄式摘要逐點式方法成對式方法序列式方法訓練語料不平衡貪婪演算法
外文關鍵詞:Spoken documentExtractive SummarizationPoint-wise ApproachPair-wise ApproachList-wise ApproachUnbalance Training DataGreedy Algorithm
相關次數:
  • 被引用被引用:0
  • 點閱點閱:302
  • 評分評分:
  • 下載下載:61
  • 收藏至我的研究室書目清單書目收藏:0
已有許多機器學習的摘要方法被應用於語音文件摘要,它們通常將文件摘要視分類問題(分兩類),嘗試從文件中挑選重要的語句做為摘要結果;然而,訓練語料不平衡的問題有時會影響這些摘要方法的效能。另一方面,藉由以增進分類正確率而訓練的摘要方法並不見得擁有較好的摘要結果。鑑於此種現象,本論文首先探討使用兩個不同的訓練準則的摘要方法,以減輕上述問題所造成的負面影響,並且得以提高摘要效能。其一為將訓練文件中成對語句之間的重要性排序資訊,做為摘要方法訓練之依據;另一則以直接最大化其摘要評估分數為準則做為計摘要方法訓練之依據。另外,一些訓練語句和特徵選取的方法也在本論文被廣泛地研究與比較。摘要實驗是在中文廣播新聞上進行;我們發現所使用的兩種訓練準則皆能夠展現出比基礎實驗方法較好的結果,但於訓練語句以及特徵選取方法似乎並不能顯地改善摘要效能。
Many of the existing machine-learning approaches to speech summarization cast important sentence selection as a two-class classification problem; however, the imbalanced data problem sometimes results in a trained speech summarizer with unsatisfactory performance. On the other hand, training the summarizer by improving the associated classification accuracy does not always lead to better summarization evaluation performance. In view of such phenomena, this thesis investigates two different training criteria to alleviate the negative effects caused by them, as well as to boost the summarizer’s performance. One is to learn the classification capability of a summarizer on the basis of the pair-wise ordering information of sentences in a training document according to a degree of importance. The other is to train the summarizer by directly maximizing the associated evaluation score. Alternatively, a few methods for training sentence and feature selection are also extensively studied and compared. Experiment results on a broadcast news summarization task show that the presented two training criteria can drive up the performance as compared to baseline summarization system, while training sentence and feature selection seems to show mixed effectiveness.
1. 緒論 1
1.1. 研究動機與目的 1
1.2. 研究內容 2
1.3. 本論文之貢獻 5
1.4. 論文架構 5
2. 相關文獻 7
2.1. 自動文件摘要背景概述 8
2.2. 自動文件摘要之方法 11
2.2.1. 非監督式模型 12
2.2.2. 監督式模型 12
2.3. 排序學習(Learning to Rank) 13
2.3.1. 逐點式方法(Point-wise Approach) 15
2.3.2. 成對式方法(Pair-wise Approach) 18
2.3.3. 序列式方法(List-wise Approach) 20
2.3.3.1. 基於評估觀點之鑑別式模型 21
2.3.3.2. 鑑別式自動文件摘要模型 22
2.3.3.3. AdaRank主要架構 22
2.3.3.4. AdaRank 演算法 24
2.4. 訓練語料不平衡 25
2.4.1. 增加正例訓練資料數量(Up-Sampling) 26
2.4.2. 減少反例訓練資料數量(Down-Sampling) 27
2.5. 摘要特徵選取 27
2.6. 自動摘要之評估方法 29
3. 實驗環境設定 31
3.1. 實驗語料 31
3.2. 摘要特徵 33
3.2.1. 摘要特徵細節介紹 34
3.2.1.1. 能量 34
3.2.1.2. 共振峰 40
3.2.1.3. 音高 49
3.2.1.4. 頻譜峰值 55
3.2.1.5. 語者資訊 60
3.2.1.6. 語句音框長度 64
3.2.1.7. 語句位置 65
3.2.1.7. 語句長度 67
3.2.1.8. 專有名詞個數 70
3.2.1.9. 停用字個數 71
3.2.1.10. 雙連詞語言模型分數 72
3.2.1.11. 詞主題模型 76
3.2.1.12. 向量空間模型 77
3.2.1.13. 潛藏式語意分析模型 81
3.2.1.14. 馬可夫隨機漫步模型 83
3.2.1.15. 生成語言模型 86
3.2.1.16. Kullback-Leibler Divergence, KL 90
3.2.1.17. 潛藏狄利克里分配 93
4. 自動摘要實驗之結果探討 98
4.1. 摘要特徵組合介紹 98
4.1.1. 基礎實驗特徵組合 98
4.1.2. 擴充摘要特徵組合 99
4.2. 逐點式方法實驗結果 101
4.2.1. 基礎摘要特徵組合之實驗結果 101
4.2.2. 擴充摘要特徵組合之實驗結果 102
4.3. 比較各種排序學習方法實驗結果 103
4.3.1. 基礎摘要特徵組合之實驗結果 103
4.3.2. 擴充摘要特徵組合之實驗結果 109
4.4. 訓練語料不平衡之實驗 113
4.5. 摘要特徵選取 115
4.5.1. 基礎摘要特徵組合之實驗結果 116
4.5.2. 擴充摘要特徵組合之實驗結果 118
5. 結論與未來展望 125
參考文獻 127
[Baxendale 1958] Baxendale, P. Machine-made index for technical literature - an experiment. IBM Journal of Research Development, 1958.
[Boser et al. 1992] B.E. Boser, I.M. Guyon, and V.N. Vapnik. A training algorithm for optimal margin classifier. In Proc. 5th ACM Workshop on Computational Learning Theory, pp. 144-152, Pittsburgh, PA, July 1992.
[Cortes et al. 1995] C. Cortes and V. Vapnik. Support Vector Networks. Machine Learning, 20, 1995.
[Climenson et al. 1961] W.D. Climenson, N.H. Hardwick, S.N. Jacobson, “Automatic syntax analysis in machine indexing and abstracting”, In American Documentation, 1961.
[Chen et al. 2009] Y. -T Chen, B. Chen and H. -M. Wang, “A probabilistic generative framework for extractive broadcast news speech summarization," IEEE Transactions on Audio, Speech and Language Processing, 17(1), 2009.
[Conroy et al. 2001] J. M. Conroy and D. P. O'leary, “Text summarization via hidden Markov models,” in Proc. of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2001, pp. 406-407.
[Chen et al. 2004] Berlin Chen, Hsin-min Wang, Lin-shan Lee, “A Discriminative
HMM/N-Gram-Based Retrieval Approach for Mandarin Spoken Documents,” ACM Transactions on Asian Language Information Processing, Vol. 3, No. 2, June 2004,
[Chen et al. 2004] B. Chen, J.-W. Kuo, W.-H. Tsai (2004), ”Lightly Supervised and Data-Driven Approaches to Mandarin Broadcast News Transcription”, in Proc. ICASSP 2004.
[Chen et al. 2005] Berlin Chen, Yi-Ting Chen, Chih-Hao Chang, Hung-Bin Chen, “Speech Retrieval of Mandarin Broadcast News via Mobile Devices”, the 9th European Conference on Speech Communication and Technology (Interspeech -Eurospeech 2005), pp. 109-112, Lisbon, Portugal, September 4-8, 2005.
[Edmundson 1969] H. P. Edmundson, “New methods in automatic extracting”, Journal of Association for Computing Machinery , 1969
[Furnas et al. 1988] G.W. Furnas, S. Deerwester, S.T. Dumais, T.K Landauer., R.
Harshman, L.A. Streeter and K.E. Lochbaum, “Information retrieval using a singular value decomposition model of latent semantic structure,” in Proc. ACM
SIGIR Conference on R&D in Information Retrieval, 1988, pp. 465-480.
[Furui et al. 2004] Sadaoki Furui, Tomonori Kikuchi, Yousuke Shinnaka, Chiori Hori,
“Speech-to-Text and Speech-to-Speech Summarization of Spontaneous Speech”, IEEE transactions on speech and audio processing, VOL. 12 No.4, July 2004.
[Garuana 1995] Caruana, Rich, "Learning Many Related Tasks at the Same Time With Backpropagation," Advances in Neural Information Processing Systems 7 (Proceedings of NIPS*94), pp. 657-664, 1995.
[Girolami 2003]M. Girolami and A. Kaban, On an equivalence between PLSI and LDA, Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 433-434, 2003.
[Chen et al. 2005] B. Chen, J.-W. Kuo, W.-H. Tsai (2005), ”Lightly Supervised and Data-Driven Approaches to Mandarin Broadcast News Transcription”, International Journal of Computational Linguistics and Chinese Language Processing, Vol. 10, March 2005.
[Chen et al. 2006] Berlin Chen, Yao-Ming Yeh, Yao-Min Huang, Yi-Ting Chen,"Chinese Spoken Document Summarization Using Probabilistic Latent Topical Information,” the 31th IEEE International Conference on Acoustics, Speech, and Signal processing (ICASSP 2006), Toulouse, France, May 14-19, 2006.
[Gong et al. 2001] Y. Gong and X. Liu, “Generic text summarization using relevance measure and latent semantic analysis,” in Proc. of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2001, 19-25.
[Gong et al. 2001] Y. Gong and X. Liu, “Generic text summarization using relevance measure and latent semantic analysis,” in Proc. ACM SIGIR Conference on R&D in Information Retrieval, 2001, pp. 19-25.
[Gong 2001] Y. Gong and X. Liu, “Generic text summarization using relevance measure and latent semantic analysis,” Proc. of the ACM SIGIR Conference on R&D in Information Retrieval, 2001
[Hirohata 2005] M. Hirohata, Y. Shinnaka, K. Iwano and S. Furui, “Sentence Extraction-Based Presentation Summarization Techniques and Evaluation Metrics,” ICASSP 2005.
[Hirohata et al. 2005] Makoto Hirohata, Yousuke Shinnaka, Koji Iwano and Sadaoki Furui, “Sentence Extraction-Based Presentation Summarization Techniques and Evaluation Metrics”, ICASSP 2005.
[Ho 2003] Y. Ho,” An initial study on automatic summarization of Chinese spoken documents,” Master Thesis, National Taiwan University, July 2003
[Hovy et al. 1998] Eduard Hovy and Daniel Marcu, “Automated Text Summarization Turorial”, COLING/ACL 1998.
[Joachims 2002] T. Joachims, Learning to Classify Text using Support Vector Machines: Methods, Theory, and Algorithms. Kluwer Academic, 2002.
[Kikuchi et al 2003] T. Kikuchi, S. Furui, and C. Hori, “Two-stage automatic speech
summarization by sentence extraction and compaction,” in Proc. IEEE and ISCA
Workshop on Spontaneous Speech Processing and Recognition, 2003, pp.207-210.
[Kupiec et al. 1999] J. Kupiec, J. Pedersen and F. Chen, “A trainable document summarizer,” in Proc. of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 1999, pp. 68-73.
[Lee and Chen 2005] L.S. Lee, B. Chen, “Spoken Document Understanding and Organization,” IEEE Signal Processing Magazine, Vol. 22, September. 2005
[Luhn et al. 1958] H. P. Luhn, “The Automatic Creation of Literature Abstracts”, IBM , Journal of Research and Development, 1958.
[Lin 2003] C.Y. Lin, “ROUGE: Recall-oriented Understudy for Gisting Evaluation,” 2003. http://www.isi.edu/~cyl/ROUGE/
[Lin et al. 2003] C.Y. Lin and Eduard Hovy, “Automatic Evaluation of Summaries Using N-gram Co-Occurrence Statistics”, Proc. of the Human Technology Conference, June, 2003, Edmonton, Canada.
[Lin et al. 2009] S. H. Lin, B. Chen, H. -M. Wang, “A comparative study of probabilistic ranking models for Chinese spoken document summarization,” ACM Transaction on Asian Language Information Processing, 8(1), pp. 3:1-3:23, 2009.
[Lin 2009] Tie-Yan Liu, ”Learning to Rank for Information Retrieval ,”Tutorial at 17th International World-Wide Web Conference(WWW) ,2009.
[Maskey et al. 2005] S. Maskey and J. Hirschberg, “Comparing lexical, acoustic/prosodic, discourse and structural features for speech summarization,” in Proc. of the Annual Conference of the International Speech Communication Association, 2005, pp. 621-624.
[Maskey et al. 2005] S. Maskey, J. Hirschberg, “Comparing Lexical, Acoustic/Prosodic, Structural and Discourse Features for Speech Summarization,” Interspeech 2005.
[Mani et al. 1999] I. Mani and M.T. Maybury, “Advances in Automatic Text Summarization,” 1999.
[Murray et al. 2005] G. Murray, S. Renals and J. Carletta, “Extractive summarization of meeting recordings,” in Proc. of the Annual Conference of the International Speech Communication Association, 2005, pp. 593-596.
[Pollock et al.1975] J. J. Pollock and A. Zamora, “Automatic Abstracting Research at Chemical Abstracts Service”, Chemical Abstracts Service, The Ohio State University, Columbus, Ohio 43210, Received July 17, 1975.
[Zhu and Penn 2005] X. Zhu, G. Penn, “Evaluation of Sentence Selection for Speech
Summarization”, in Proc the 2nd International Conference on Recent Advances in Natural Language Processing (RANLP-05), pp. 39-45. September 2005.
[Penn et al. 2008] G. Penn and X. Zhu, “A critical reassessment of evaluation baselines for speech summarization,” in Proc. of the Annual Meeting of the Association for Computational Linguistics, 2008, pp. 470-478.
[Salton et al. 1968] G. Salton and M. E. Lesk, “Computer evaluation of indexing and text processing,” Journal of the ACM, vol. 15, no. 1, pp. 8-36, 1968.
[Shen et al. 2007] D. Shen, J. –T. Sun, H. Li, Q. Yang, Z. Chen, “Document summarization using conditional random fields,” in Proc. of the International Joint Conference on Artificial Intelligence, 2007, pp. 2862-2867.
[Snack] http://www.speech.kth.se/snack/
[Tao 2009] Tao Qin, Tie-Yan Liu, Hang Li, “A general approximation framework for direct optimization of information retrieval measures,” in Proc. of the Springer Science+ Business Media, LLC 2009
[VanDijk 1980] T.A. vanDijk, “Macrostructures: An interdisciplinary study of global structures in discourse, interaction, and cognition”, Lawrence Erlbaum, Hillsdale, 1980.
[Wan et al. 2008] X. Wan and J. Yang, “Multi-document summarization using cluster-based link analysis,” Proc. of the 31st Annual International ACM SIGIR, 2008.
[Wang et al. 2005] H.M. Wang, B. Chen, J. W. Kuo, and S. S. Cheng, “MATBN: A Mandarin Chinese Broadcast News Corpus“, Internation Journal of Computational Linguistics and Chinese Language Processing, Vol. 10, June 2005.
[Xie 2009] Shasha Xie, Yang Liu, ”Improving supervised learning for meeting summarization using sampling and regression,”Elsevier 2009.
[Geng 2007] Xiubo Geng, Tie-Yan Liu, Tao Qin, Hang Li.”Feature Selection for Ranking,”SIGIR’07, Month 1-2.
[Xu et al. 2007] J. Xu and H. Li ”AdaRank: A Boosting Algorithm for Information Retrieval,” In Proc. of the 30th annual international ACM SIGIR conf. July 2007
[Yue et al. 2007] Y. Yue, T. Finley, F. Radlinski, and T. Joachims. “A support vector
method for optimizing average precision.” SIGIR ’07: Proceeding of the 30th annual international ACM SIGIR conference in Research and development information retrieval, pp. 271-278, 2007.
[Zhang et al. 2007] J. Zhang, H. -Y. Chan, and P. Fung, “A comparative study on speech summarization of broadcast news and lecture speech,” in Proc. of the Annual Conference of the International Speech Communication Association, 2007, pp. 2781-2784.
[王小川 2009] 王小川,“語音訊號處理”全華科技圖書, 2009(修訂二版)
[陳怡婷 2007] 陳怡婷,中文語音資訊摘要-模型與特徵之改進,碩士論文,國立臺灣師範大學資訊工程研究所,2007。
[游斯涵2009] 游斯涵,使用機器學習方法於語音文件檢索之研究,碩士論文,國立臺灣師範大學資訊工程研究所,2009。
[陳怡婷 et al. 2006] 陳怡婷、游斯涵、李家豪、陳柏琳,“中文語音文件摘要使用主題混合模型,"第十一屆人工智慧與應用研討會, 2006。
[何遠 2003] 何遠,”中文口語文件自動摘要之初步研究”,碩士論文,國立台灣大學電信工程學研究所,2003年。
[葉鎮源 2002] 葉鎮源,”文件自動畫摘要方法之研究及其在中文文件的應用”, 碩士論文,國立交通大學資訊科學研究所,2002年。
[黃建霖 2004] 黃建霖,”應用平行語料和語意相依法則於中文語音文件之摘要”,碩士論文,國立成功大學資訊工程學系,2004年。
[林士翔 2010 ] 林士翔、陳柏琳,”現階段語音文件摘要研究之簡介”,國立台灣師範大學資訊工程系。
[黃耀民 2005] 黃耀民,以字句擷取為基礎並應用於文件分類之自動摘要之研究,碩士論文,國立臺灣師範大學資訊工程研究所,2005。
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top