語(yǔ)義排歧（Word Sense Disambiguation）一直是自然語(yǔ)言處理（Natural Language Processing）和語(yǔ)義學(xué)研究領(lǐng)域一個(gè)非常重要的課題,幾乎覆蓋了各種自然語(yǔ)言處理系統(tǒng),其中包括信息檢索,機(jī)器翻譯,關(guān)鍵詞的提取,語(yǔ)音識(shí)別,文本分類(lèi)和自動(dòng)文摘。語(yǔ)言學(xué)家和計(jì)算機(jī)科學(xué)家在探索自然語(yǔ)言的歧義問(wèn)題上做了大量的工作,取得了很大的成績(jī)。但現(xiàn)有的對(duì)自然語(yǔ)言排歧的研究主要集中在語(yǔ)法、詞典、簡(jiǎn)單的詞匯詞義層面上,對(duì)上下文、語(yǔ)義、語(yǔ)境、語(yǔ)用等知識(shí)和信息雖有涉及,但對(duì)這些信息的挖掘還相當(dāng)有限。對(duì)于情態(tài)助動(dòng)詞這樣語(yǔ)義更加模糊、對(duì)語(yǔ)境更為敏感的詞類(lèi)的語(yǔ)義排歧,目前尚未發(fā)現(xiàn)。語(yǔ)義排歧的研究對(duì)象是語(yǔ)言,將語(yǔ)言學(xué)的研究成果用到語(yǔ)義排歧中,將有利于打破語(yǔ)義消歧的瓶頸,推動(dòng)其更深入的發(fā)展。特別是在情態(tài)意義方面,從《馬氏文通》開(kāi)始,語(yǔ)言學(xué)家對(duì)漢語(yǔ)情態(tài)助動(dòng)詞做了深入且全面的研究。這些研究成果為構(gòu)建漢語(yǔ)情態(tài)動(dòng)詞的語(yǔ)義排歧模型的設(shè)想提供了充足的理論基礎(chǔ)。另外,語(yǔ)義消歧的發(fā)展也將服務(wù)于語(yǔ)言學(xué)研究。情態(tài)助動(dòng)詞的自動(dòng)語(yǔ)義排歧,能夠?qū)崿F(xiàn)情態(tài)助動(dòng)詞的語(yǔ)義的自動(dòng)標(biāo)注,從而為語(yǔ)言學(xué)家運(yùn)用大規(guī)模語(yǔ)料庫(kù)研究情態(tài)助... 

【文章頁(yè)數(shù)】：128 頁(yè)

【學(xué)位級(jí)別】：碩士

【文章目錄】：
摘要
Abstract
Chapter 1 Introduction
    1.1 Background of this study
    1.2 Objectives of the present study
    1.3 Rationale of the study
    1.4 Outline of the present study
Chapter 2 Literature Review
    2.1 Approaches to word sense disambiguation
    2.2 Word sense disambiguation studies abroad
    2.3 Studies of WSD in China
    2.4 Studies of Chinese modal verbs
Chapter 3 Methodology and Data Collection
    3.1 Connectionism
        3.1.1 Human and Artificial Neurons
        3.1.2 Structure of Artificial Neural Network
        3.1.3 Advantages of Artificial Neural Networks
        3.1.4 The learning process
        3.1.5 Back propagation network
    3.2 Research method and data collection
Chapter 4 Sense Categorization of ‘能
    4.1 Study of sense categorization on ‘能’
    4.2 Sense categorization of ‘能’proposed by Li
        4.2.1 Epistemic modality
        4.2.2 Participant-internal modality
        4.2.3 Participant-external modality
        4.2.4 Deontic modality
Chapter 5 The Construction of the Neural Network Model for Word Sense Disambiguation of ‘能’
    5.1 WSD Model
    5.2 Construct two sense-tagged corpora of ‘能’
    5.3 Feature extraction
    5.4 Transfer linguistic features into vectors
        5.4.1 Define the input vectors
        5.4.2 Define the output vectors
    5.5 Determine the number of nodes in hidden layer
    5.6 Model constructing in Matlab
        5.6.1 About Matlab
        5.6.2 Construct neural network model in Matlab
    5.7 Summary
Chapter 6 Further Study
    6.1 Distribution of four senses of ‘能’in corpora
    6.2 Co-occurrence of ‘能’with linguistic features
        6.2.1 Co-occurrence of ‘能’with syntactic features
        6.2.2 Co-occurrence of ‘能’with semantic features
    6.3 The contribution of semantic features and syntactic features to word of ‘能'
    6.4 Summary
Chapter 7 Conclusion
References
Appendix I
Appendix Ⅱ
Appendix Ⅲ
Appendix Ⅳ
Acknowledgements
作者簡(jiǎn)介


【參考文獻(xiàn)】：
期刊論文
[1]基于可拓學(xué)理論的漢語(yǔ)詞義消歧[J]. 盧志茂,劉挺,李生.  哈爾濱工業(yè)大學(xué)學(xué)報(bào). 2006(12)
[2]基于多分類(lèi)器決策的詞義消歧方法[J]. 全昌勤,何婷婷,姬東鴻,余紹文.  計(jì)算機(jī)研究與發(fā)展. 2006(05)
[3]利用BP神經(jīng)網(wǎng)絡(luò)的中文詞義消歧模型[J]. 何婷婷,謝芳.  華中師范大學(xué)學(xué)報(bào)(自然科學(xué)版). 2005(04)
[4]基于MDL聚類(lèi)的無(wú)導(dǎo)詞義消歧[J]. 陳浩,何婷婷,姬東鴻.  小型微型計(jì)算機(jī)系統(tǒng). 2005(10)
[5]情態(tài)與漢語(yǔ)情態(tài)動(dòng)詞[J]. 朱冠明.  山東外語(yǔ)教學(xué). 2005(02)
[6]情態(tài)動(dòng)詞“能”在交際過(guò)程中的義項(xiàng)呈現(xiàn)[J]. 王偉.  中國(guó)語(yǔ)文. 2000(03)
[7]基于神經(jīng)網(wǎng)絡(luò)的漢語(yǔ)口語(yǔ)多義選擇[J]. 王海峰,高文,李生.  軟件學(xué)報(bào). 1999(12)
[8]助動(dòng)詞“想”和“要”的區(qū)別[J]. 張維耿.  語(yǔ)言教學(xué)與研究. 1982(01)



本文編號(hào)：3652221