跳到主要內容

臺灣博碩士論文加值系統

(52.203.18.65) 您好!臺灣時間:2022/01/19 16:47
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

我願授權國圖
: 
twitterline
研究生:黃豐隆
研究生(外文):Feng-Long Huang
論文名稱:使用一個三層分類器來釐清中文文轉音系統中非文字符號的語意
論文名稱(外文):Disambiguating the Senses of Non-Text Symbols for Mandarin TTS Systems with a Three-Layer Classifier with a Three-Layer Classifier
指導教授:余明興余明興引用關係
指導教授(外文):Ming-Shing Yu
學位類別:博士
校院名稱:國立中興大學
系所名稱:應用數學系
學門:數學及統計學門
學類:數學學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:英文
論文頁數:96
中文關鍵詞:語義釐清非文字符號三層分類器拜式定理投票策略
外文關鍵詞:Sense disambiguationnon-text symbolThree-Layer ClassifierBayesian theoryvoting schemes
相關次數:
  • 被引用被引用:2
  • 點閱點閱:597
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:2
在文章中常會出現各式各樣的非文字符號, 如 ‘/’,’:’,’-’等。這些非文字符號的口語表示式會隨著它們在文章中的意義而改變。本論文提出一個三層分類器(Three-Layer Classifier, TLC)架構,可以有效解決中文文轉音系統 (Text-to-Speech, 簡稱TTS) 中非文字符號意義的岐義問題。
在三層分類器中,釐清非文字語義的程序由第一層起循序使用。第一層包含兩個元件:樣式表與決策樹。如果第一層可以釐清符號的語義,解決程序就此結束,否則其他兩層將會被啟動。第二層依據拜氏定理,採用投票方法計算出釐清分數 (Disambiguation score)。我們分析句子中記號的多種特徵並且相互比較,以達到更好的正確性;這些特徵會影響到投票方法的效果。第三層依照信心演算法,可能使用到替代方案以達到更高的正確性。
本論文章節內容編排如下: 第一章首先說明論文所研究問題的背景與範圍。第二章探討中文相關特性與資訊和以前在釐清語義歧義方面有關的論文。第三章描述我們所提出整個模式的架構。第四章說明TLC中第一層 — 各種知識應用 (Knowledge Utilization), 的功能與做法。第五章使用拜式定理推導第二層 — 投票策略 (Voting Scheme), 的方法與功能; 文章句子中多種符號單元 (如中文字或詞) 與投票方法(如喜好度或贏者全拿法), 會被分析並評量其效益。第六章說明第三層 — 提昇信心 (Confidence Enhancement), 提出如何採取替代方法以提高整體正確性。 最後,提出結論與未來可能進一步探討的方向。
實驗顯示我們提出的策略,即使在少量語料下,也能學習得很好。訓練與測試的正確率分別高達99.8%與97.5%。
Various kinds of non-text symbols appear in texts (e.g., “/”, “:”, and “-“). The oral expressions of these symbols may vary with their senses. This dissertation proposes an approach of Three-Layer Classifier (TLC) which can disambiguate the senses of these symbols effectively.
The layers within TLC are employed in sequence. The 1st layer is composed of two components: pattern table and decision tree. If this layer can disambiguate the sense of the target symbol, the disambiguation task stops. Otherwise the next two layers will be triggered. In such a situation, the procedure will go through the TLC. Based on the Bayesian theory, the 2nd layer adopts the voting scheme to compute the disambiguation score. Several features of token, which may affect the effectiveness of our voting scheme, are analyzed and compared with each other to achieve better accuracy.
This dissertation is organized as follows: in Chapter 2, we first present some related information of Chinese text and previous works on sense disambiguation (SD). Chapter 3 focuses on the overall structure of our proposed model. Chapter 4 elaborates the 1st layer - Knowledge Utilization, in TLC. In Chapter 5, we present the 2nd layer - Voting Scheme, in TLC. Several parameters like tokens unit (e.g., Mandarin words or characters) and scoring schemes (e.g., preference and winner-take-all scoring) are evaluated in our experiments. In Chapter 6, the 3rd layer - Confidence Enhancement, is elaborated in detail. According to the algorithm confidence of sense disambiguation, the 3rd layer may exploit an alternative model to enhance the performance. Finally, the conclusions and future researches are presented in Chapter 7.
We implement all the various methods proposed in this dissertation. Experiments show that our approaches can learn well even with only a small amount of data. The overall accuracies of training and testing sets are 99.8% and 97.5%, respectively.
Chapter 1 Introduction
Chapter 2 Related Information and Previous Works
Chapter 3 The Proposed Approach ─
Three Layer Classifier (TLC)
Chapter 4 The First Layer of TLC ─ Knowledge Utilization
Chapter 5 The Second Layer of TLC ─ Voting Scheme
Chapter 6 The Third Layer of TLC ─ Confidence Enhancement
Chapter 7 Conclusions and Future Works
Acknowledgement
References
Appendix
Publications
Brown P., Della Pietra S., Della Pietra V. and Mercer R., 1991, Word Sense Disambiguation Using Statistical Methods, Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, Berkeley, pp. 264- 270.
Brown P. F., Pietra V. J., deSouza P. V., Lai J. C., and Mercer R. L., 1992, Class-Based n-gram Models of Natural Language, Computational Linguistics, Vol. 18, No. 4, pp. 467-479.
Charpentier F. J., Stella M. C., 1986, Diphone Synthesis Using an Overlap-Add Technique for Speech Waveforms Concatenation, IEEE International conference on Acoustic, Speech and Signal Processing, pp. 2015-2020.
Chen F.-Y., Tsai P.-F., Chen K.-J. and Huang C.-R., August 1999, Sinica Treebank, Computational Linguistics and Chinese Language Processing, Vol. 4, No. 2, pp. 87-104.
Chen K.-J., Lin S.-H. and Chang L.-P., 1994, A Predictive Tagger for Chinese Corpora, Proceedings of Research on Computational Linguistics Conference (ROCLING VII), pp. 111-126.
Chen K.-J., August 1996, A Model for Robust Chinese Parser, Computational Linguistics and Chinese Language Processing, Vol. 1, No. 1, Taiwan, pp. 183-204.
Chen S. F. and Goodman J., 1999, An Empirical Study of Smoothing Techniques for Language Modeling, Vol. 13, Computer Speech and Language, pp. 359-394.
Chen S. H., Hwang S. H. and Wang Y.-R., 1998, An RNN-based Prosodic Information Synthesizer for Mandarin Text-to-Speech, IEEE Trasn. Speech Audio Process, Vol. 6, No. 3, pp. 226-239.
Chiang T.-H., Chang J.-S., Lin M.-Y. and Su K.-Y., 1996, Statistical Word Segmentation, Journal of Chinese Linguistics, No. 9, pp.147-174.
Chinese Knowledge Information Processing (CKIP) Group, 1995, Technical Report: 95-02. The Content of Academia Sinica Balanced Corpus (ASBC), Academia Sinica, Taiwan.
Duda R. O. and Hart P. E., 1973, Pattern Classification and Scene Analysis, John Wiley and Sons, New York.
Dunning T., 1993, Accurate Methods for the Statistics of Surprise and Coincidence, Computational Linguistics, Vol. 19, pp. 61-74.
Fan C.-K., Tsai W.-H, 1988, Automatic Word Identification in Chinese Sentences by the Relaxation Technique, Computer Processing of Chinese and Oriental Languages, Vol. 4, pp. 33-56.
Fujii A., Inui K., Tokunaga T. and Tanaka H., 1998, Selective Sampling for Example-Based Word Sense Disambiguation, Computational Linguistics, Vol. 24, No. 4, pp 573-597.
Gale W. A., 1995, Cognition, Computation and Formal Systems: some of Tomos Havranek’s Interests and Disambiguating Word Senses, Computational Statistics and Data Analysis, Vol. 19, 135-148.
Gale W. A., Church K. W., and Yarowsky D., 1992, A Method for Disambiguating Word Sense in a Large Corpus, Computer and the Humanities, Vol. 26.
Golding A. R., 1995, A Bayesian Hybrid Method for Context-Sensitive Spelling Correction, Proceedings of the Third Workshop on Very Large Corpora, pp. 39-53, Boston, USA.
Good I. J., 1953, The Population Frequencies of Species and the Estimation of Population Parameters, Biometrika, Vol. 40, pp. 237-264.
Hwang F.-L. and Yu M.-S. and Wu M.-J., 2000, The Improving Techniques for Disambiguating Non-Alphabet Sense Category, Proceedings of Research on Computational Linguistics Conference (ROCLING) XIII, Taipei, Taiwan, pp. 67-86.
Huang C.-R., 1995, Introduction to the Academic Sinica Balanced Corpus, Proceedings of Research on Computational Linguistics Conference, Taiwan, pp. 81-99.
Huang F.-L. and Yu M.-S., October 2001, Analyzing Statistical Properties of Smoothing Methods for Language Models, to appear in Proceedings of, IEEE System, Man and Cybernetics Conference (IEEE SMC, 2001), Tucson, Arizona, U. S. A., pp. 512-517.
Ide N. and Veronis J., 1998, Introduction to the Special Issue on Word Sense Disambiguation: The State of the Art, Computational Linguistics, Vol. 24, No. 1, pp 1-40.
Jelinek F. and Mercer R. L., 1980, Interpolated Estimation of Markov Source Parameters from Spars Data, Proceedings of the Workshop on Pattern Recognition in Practice, North-Holland, Amsterdam, The Northlands, pp. 381-397.
Jurafsky D. and Martin J. H., Speech and Language Processing, Printice Hall, 2000.
Katz S. M., March 1987, Estimation of Probabilities from Sparse Data for the Language Models Component of a Speech Recognizer, IEEE Trans. on Acoustic, Speech and Signal Processing, Vol. ASSP-35, pp. 400-401.
Klatt D. H., 1987, Review of Text-To-Speech Conversion for English, Acoustic Society America, Vol. 82, No. 3, pp. 737-793.
Leacock C., Chodorow M., 1999, Using Corpus Statistics and WordNet Relation for Sense Identification, Computational Linguistics, Vol. 24, No.1, pp147-165.
Lee L.-S., Tseng C.-Y. and Ouh-Young M., September 1989, The Synthesis Rules in a Chinese Text-to-Speech System, IEEE Trans. on Acoustics, Speech and Signal Processing, Vol. 37, No. 9, pp. 619-621.
Lee H., Baek D.-H. and Rim H.-C., 1997, Word Sense Disambiguation Based on the Information Theory, Proceedings of Research on Computational Linguistics Conference International Conference (ROCLING X), Taiwan, pp. 49-58.
Lee L.-S., Tseng C.-Y., Gu H.-Y., Liu F.-H., Chang C.-H., Lin Y.-H., Lee Y., Tu S.-L., Hsieh S.-H., and Chen C.-H., April 1993, Golden Mandarin (I)─A Real-Time Mandarin Speech Dictation Machine for Chinese Language with Very Large Vocabulary, IEEE Trans. On Speech and Audio Processing, Vol.1, No. 2, pp. 158-179.
Li J. and Huang C., August 1999, A Model for Word Sense Disambiguation, International Journal of Computational Linguistics and Chinese language Processing, Taiwan, pp. 1-19.
Liang N. Y. and Zhen Y. B., 1991, A Chinese Word Segmentation Model and a Chinese Word Segmentation System PS-CWSS, COLIPS, Vol. 1, pp. 51-55.
Merialdo A., 1990, Tagging Text with a Probabilistic Model, Proceedings of the IBM Natural Language ITL, Paris, France, pp. 161-172.
Miller G. A. and Charles W. G., 1991, Contextual Correlates of Semantic similarity, Language and Cognitive Processes, Vol. 6, No. 1, pp.1-28.
Ney H. and Essen U., 1991, On Smoothing Techniques for Bigram-Based Natural Language Modeling, IEEE International conference on Acoustic, Speech and Signal Processing, pp. 825-828.
Nie J. Y., Ren X. and Brisebois M., 1995, A Unifying Approach to Segmentation of Chinese and its Application to Text Retrieval, Proceedings of Research on Computational Linguistics Conference (ROCLING VIII), Taiwan, pp. 175-190, pp.1-28.
Schutze H., 1995, Ambiguity and Language Learning: Computational and Cognitive Models, Ph. D. Thesis, Stanford University.
Sproat R., and Shih C., 1991, A Statistical Method for Finding Word Boundaries in Chinese Text, Computer Processing of Chinese and Oriental Languages, Vol. 4, No. 4, pp. 336-351.
Shih C. L. and Sproat R., 1996, Issues in Text-to-Speech Conversion for Mandarin, Computational Linguistics Chinese Language Process, Vol. 1, pp. 37-86.
Sproat R., Hirschberg J. and Yaroswky D., 1992, A Corpus-Based Synthesizer, Proceedings of International Conference on Spoken Language Processing, Banff.
Streiter O., 2000, Parsing Chinese by Examples, Proceedings of Research on Computational Linguistics Conference (ROCLING) XIII, Taiwan, pp. 41-66.
Su K.Y. and Chang J. S., 1992, Semantic and Syntactic Aspect of Score Function, Proceedings of COLING-88, pp 642-644.
Su K. Y., Chiang T. H. and Chang J. S., August 1996, An Overview of Corpus-Based Statistical Oriented (CBSO) Techniques for Natural Language Processing, Computational Linguistics and Chinese Language Processing, Vol. 1, No. 1, pp.101-157.
Towell G. and Voorhees E. M., 1999, Disambiguating Highly Ambiguous words, Computational Linguistics, Vol. 23, No. 3, pp. 125-145.
Uramoto Naohiko, 1994, Example-Based Word Sense Disambiguation, IEICE Transactions on Information and Systems, E77-D92, pp. 240-246.
Veronis J. and Ide N., 1990, Word sense Disambiguation with Very Large Natural Corpus Extracted from Machine Readable Dictionaries, in Proceeding of COLING-90, 1990.
Witten I. H. and Bell T. C., Jul. 1991, The Zero-Frequency Problem: Estimating the Probabilities of Novel Event in Adaptive Text Compression, IEEE Transactions on Information Theory, Vol. 37, No. 4, pp. 1085-1094.
Wu C.-H. and Chen J.-H., 2001, Automatic Generation of synthesis Units and Prosodic Information for Chinese Concatenative synthesis, Speech Communication, Vol. 35, pp. 219-237.
Yao T. S., Zhang G. P. and Wu Y. M., 1990, A Rule-based Chinese Automatic Segmentation Expert System, Journal of Chinese Information Processing, Vol. 5, pp. 38-47.
Yarowsky D., 1994, Decision Lists for Lexical Ambiguity Resolution: Application to Accent Restoration in Spanish and French, Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics, Las cruces, NM, pp. 88-95.
Yarowsky D., 1997, Homograph Disambiguation in Text-to Speech Synthesis, in van J. Santen, Sproat R., Olive J. and Hirschberg J., (Eds), Progress in Speech Synthesis, Springer-Verlag, New York, pp.159-175.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top