English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  Items with full text/Total items : 113311/144292 (79%)
Visitors : 50941073      Online Users : 943
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    政大機構典藏 > 資訊學院 > 資訊科學系 > 學位論文 >  Item 140.119/119215
    Please use this identifier to cite or link to this item: https://nccur.lib.nccu.edu.tw/handle/140.119/119215


    Title: 從文本語境中建構詞彙概念連結路徑之研究
    A study on constructing lexical concept connection link based on context words
    Authors: 羅郁雯
    Lo, Yu-Wen
    Contributors: 劉吉軒
    Liu, Jyi-Shane
    羅郁雯
    Lo, Yu-Wen
    Keywords: 詞彙關聯
    Word2vec
    概念連結路徑
    Word associations
    Word2vec
    Concept connection link
    Date: 2018
    Issue Date: 2018-08-06 18:13:00 (UTC+8)
    Abstract: 本研究使用Word2vec的自然語言處理技術,分析中研院平衡語料庫的文本資料,以Word2vec 的餘弦相似性作為計算連結路徑的基準,建構兩種詞彙概念連結路徑,探討不同詞彙關係的詞組在概念連結路徑上所呈現的結果。將兩個詞彙依照不同連結關係分成同義詞組,反義詞組,共現詞組以及隨機詞組四種類型的詞組,透過雙向概念連結路徑及詞彙相似連結路徑分析詞彙之間的概念連結路徑,找出各連結關係的詞組在連結路徑上產生的概念連結路徑,分析兩個詞彙在路徑中產生關聯性的各詞彙之涵義,並且比較各詞組的連結路徑結果以及路徑的差異性。期能提供語言研究和聯想學習另一種用以判定詞彙概念關係的方法。
    This paper aims at providing the analytic results of relationship between two vocabulary which link by the meaning of words. By applying Natural Language Processing by Word2vec Model, analyze textual data in Sinica Corpus and constructing two lexical concept connection link base on cosine similarity of Word2vec. As the result, the conceptual linkage in the lexical semantic relation in different phrases be explored.According to different lexical semantic relation divided into four types of phrases: synonym phrases, antisense phrase, co-occurrence phrase and random phrase,and constructing two concept connection link: the Bilateral concept connection link and the Words similar connection link,find out the concept connection link by the phrase of different lexical semantic relation.Analyze the meaning of each word in concept connection link,and compare the result of the connection link of different lexical semantic relation phrase.Expected to provide language research and association learning another way to determine the lexical
    concept connection link based.
    Reference: [1] 黃居仁,語意網、詞網與知識本體:淺談未來網路上的知識運籌,佛教圖書館館訊,第33 期:頁1-21,2003
    [2] 知網: http://www.keenage.com/zhiwang/c_zhiwang.html
    [3] 廣義知網: http://ehownet.iis.sinica.edu.tw/index.php
    [4] 林素朱,廣義知網的詞彙知識架構與語意表達,當代語言學,第2 期:頁 177-194,2013
    [5] T. Mikolov, K. Chen, G. Corrado, J. Dean, “Efficient Estimation of Word Representations in Vector Space ,”arXiv preprintarXiv:1301.3781,2013
    [6] 中央研究院現代漢語標記語料庫4.0:http://asbc.iis.sinica.edu.tw/
    [7] 中央研究院漢語料庫的內容與說明: http://asbc.iis.sinica.edu.tw/
    [8] CKIP 中文詞知識庫小組:http://ckip.iis.sinica.edu.tw/CKIP/conceptnet.htm
    [9] 廣義知網知識本體架構說明:http://ckip.iis.sinica.edu.tw/taxonomy/taxonomy-doc.htm
    [10] 陳克健、黃淑齡、施悅音、陳怡君,多層次概念定義與複雜關係表達-繁體字知網的新增架構漢語詞彙語義研究的現狀與發展趨勢,國際學術研討會,北京大學,2005
    [11] 李政儒、游基鑫、陳信希,廣義知網詞彙意見極性的預測,語言學期刊,17(2):頁21-36,2012
    [12] A. M. Collins, E. F. Loftus , “A Spreading-Activation Theory of Semantic Processing,”Psychological Review, 82, pp.407-428 ,1975
    [13] 林右敏,在圖文聯想遊戲中探討玩家的思考風格對聯想歷程的影響,新竹市,國立交通大學,2007
    [14] C. D. Holley, D. F. Dansereau, (Eds.), “Spatial Learning Strategies: Techniques,Applications, and Related Issues , ”New York: Academic Press ,1984
    [15] 林清山(譯),R.E.Mayer 著,教育心理學 認知取向(Educational psychology: A aognitive approach),台北市:遠流,1997
    [16] 余民寧,有意義的學習:概念構圖之研究,台北市:商鼎文化出版社,1997
    [17] 黃博聖、陳學志、黃鴻程、劉政宏,「詞彙聯想策略擴散性思考測驗」之編製,測驗學刊,第56 輯第2 期:頁153-177,2009
    [18] 黃博聖、陳學志、劉政宏,「中文詞彙遠距聯想測驗?之編製及其信、效度報告,測驗學刊,第56 輯第2 期:頁581-607,2012 (12)
    [19] 高照明,中文詞彙語意資料的整合及擷取:詞彙語意學的觀點,第十九屆自然語言與語音處理研討會論文集,台北,頁257-272 ,2007
    [20] 詞向量-LRWE 模型:https://www.cnblogs.com/chenbjin/p/7106139.html
    [21] 現代漢語?語義場 同義詞 反義詞:https://kknews.cc/zh-tw/education/ae98nln.html
    [22] 洪蘭(譯),George Miller 作,詞的學問—發現語言的科學,遠流,2002
    [23] 趙逢毅、鍾曉芳,基於字典釋義關聯方法的同義詞概念擷取:以《同義詞詞林(擴展版)》為例,中文計算語言學期刊,Vol.18,No.2,頁35-56,2013(6)
    [24] G. E. Hinton, “Learning distributed representations of concepts,”Proceedings of the Eighth Annual Conference of the Cognitive Science Society, Vol.1 , 1986
    [25] 寧建飛、劉降珍,融合 Word2vec 與 TextRank 的關鍵詞抽取研究,現代圖書情報技術:頁20-27,2016 (6)
    [26] 熊富林、鄧怡豪、唐曉晟,Word2vec 的核心架構及其應用,南京師範大學學報(工程技術版),VoL.15 No.1,2015
    [27] TF-IDF 與餘弦相似性的應用(二)找出相似文章:http://www.ruanyifeng.com/blog/2013/03/cosine_similarity.html
    [28] 教育部國語重編字典 :http://dict.revised.moe.edu.tw/cbdic/
    [29] J. Pennington, R .Socher, C. Manning, “Glove: Global vectors for word representation,”In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 1532–1543, 2014.
    [30] Word2vec 中的數學原理詳解:http://blog.csdn.net/itplus/article/details/37969519
    [31] Xin Rong,“Word2vec Parameter Learning Explained,” arXiv preprintarXiv:1411.2738,2014.
    [32] Yoav Goldberg , Omer Levy , “Word2vec Explained: Deriving Mikolov et al.’s Negative-Sampling Word-Embedding Method,”arXiv preprint arXiv:1402.3722,2014
    [33] 向量能蘊含多少單詞本身的意思信息?https://www.getit01.com
    [34] 維基百科:http://zh.wikipedia.org/
    Description: 碩士
    國立政治大學
    資訊科學系
    104753042
    Source URI: http://thesis.lib.nccu.edu.tw/record/#G0104753042
    Data Type: thesis
    DOI: 10.6814/THE.NCCU.CS.006.2018.B02
    Appears in Collections:[資訊科學系] 學位論文

    Files in This Item:

    File SizeFormat
    304201.pdf2906KbAdobe PDF212View/Open


    All items in 政大典藏 are protected by copyright, with all rights reserved.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,惟仍請適度,合理使用本網站之內容,以尊重著作權人之權益。商業上之利用,則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作,已盡力防止侵害著作權人之權益,如仍發現本網站之數位內容有侵害著作權人權益情事者,請權利人通知本網站維護人員(nccur@nccu.edu.tw),維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback