臺灣人文及社會科學引文索引資料庫系統

:::

詳目顯示

回上一頁
第 1 筆 / 總合 1 筆   第一頁 上一頁 下一頁 最後一頁
/1頁
題名：從詞網出發的中文複合名詞的語意表達
書刊名：International Journal of Computational Linguistics & Chinese Language Processing
作者：柯淑津
出版日期：2003
卷期：8:2
頁次：頁93-107
主題關鍵詞：詞網；中文複合名詞；語意表達；自然語言處理；WordNet
原始連結：連回原系統網址new window
相關次數：
  • 被引用次數被引用次數:期刊(2) 博士論文(0) 專書(0) 專書論文(0)
  • 排除自我引用排除自我引用:2
  • 共同引用共同引用:0
  • 點閱點閱:16
WordNet 提供豐富的詞彙語意資訊，因此對於自然語言處理相關研究有很大的 幫助。但是由於Princeton WordNet 的語意資訊僅以英文的形式呈現，為了能 讓WordNet 所蘊含的豐富資源也能應用到中文相關處理，我們試圖利用雙語 字典等多項已存在的資源做為橋樑，希望能將英文WordNet 的豐富資源自動 引介到中文。但是，在我們觀察這些連結英文WordNet 與雙語字典所產生的 初步結果後，發現由於語言之間的藩籬以及雙語字典的目標語詞彙大都偏向於 解釋等多種原因，使得英文同義詞集(Synset)所對應到的中文翻譯，常是一些 不具結構性的中文複合詞、片語、甚至是一長串的句子，而不是獨立的中文詞 彙。這樣的現象與中文詞網應以詞彙為基本元件的要求相違背。因此，本研究 將針對這種現象作進一步的處理。 本文的主要目標有下列兩項：首先，自中文複合詞找出最能代表其意義的中心 詞彙，及若干個特徵詞彙。其次，將這些詞彙進一步以語意概念形式表達出來。 第一個部分，我們透過語法結構分析來完成。至於，第二個部分，詞彙的語意 我們透過知網的概念特徵來表示。當然，在中文詞彙轉為詞義概念的部分，是 存在著歧義現象的。辨識語意歧義的方法，我們除了用到詞彙的詞性之外，還 透過WordNet 的上位關係來降低歧義度。我們以名詞部分進行實驗，實驗結 果顯示在語意標示方面，可達到93.5%的應用率以及93.8%的正確率。
WordNet provides plenty of lexical meaning; therefore, it is very helpful in natural language processing research. Each lexical meaning in Princeton WordNet is presented in English. In this work, we attempt to use a bilingual dictionary as the backbone to automatically map English WordNet to a Chinese form. However, we encounter many barriers between the two different languages when we observe the preliminary result for the linkage between English WordNet and the bilingual dictionary. This mapping causes the Chinese translation of the English synonymcollection (Synset) to correspond to unstructured Chinese compound words, phrases, and even long string sentence instead of independent Chinese lexical words. This phenomenon violates the aim of Chinese WordNet to take the lexical word as the basic component. Therefore, this research will perform further processing to study this phenomenon. The objectives of this paper are as follows: First, we will discover core lexical words and characteristic words from Chinese compound words. Next, those lexical words will be expressed by means of conceptual representations. For the core lexical words, we use grammar structure analysis to locate such words. For characteristic words, we use sememes in HowNet to represent their lexical meanings. Certainly, there exists a problem of ambiguity when Chinese lexical words are translated into their lexical meanings. To resolve this problem, we use lexical parts-of-speech and hypernyms of WordNet to reduce the lexical ambiguity. We experimented on nouns, and the experimental results show that sense disambiguation could achieve a 93.8% applicability rate and a 93.5% correct rate.
期刊論文
1.Miller, G. A.(1990)。Five papers on WordNet。International Journal of Lexicography，3(4)。  new window
2.Dice, L. R.(1945)。Measure of the Amount of Ecologic Association between Species。Journal of Ecology，26，297-302。  new window
3.Chen, J. N.、Chang, Jyun-Sheng(1998)。TopSense: A Topical Sense Clustering Method based on Information Retrievel Techniques on Machine Readable Resources。Computational Linguistics，24(1)，61-95。  new window
4.Dagan, Ido、Itai, Alon(1994)。Word Sense Disambiguation Using a Second Language Monolingual Corpus。Computational Linguistics，20(4)，563-596。  new window
會議論文
1.Chang, Jyun-Sheng、Ker, S. J.、Chen, M. H. C.(1998)。Taxonomy and Lexical Semantics-From the Perspective of Machine Readable Dictionary199-212。  new window
2.陳信希、Lin, Chi-ching(2000)。Sense-Tagging Chinese Corpus。Hong Kong。7-14。  new window
3.Mandala, R.、Tokunaga, Takenobu、Tanaka, Hiroshi(1998)。The use of WordNet in Information Retrieval。New Brunswick, NJ : ACL ; San francisco, CA。31-37。  new window
4.Jing, H.(1998)。Usage of WordNet in Natural Language Generation。New Brunswick, NJ : ACL ; San francisco, CA。128-134。  new window
5.Guthrie, J.、Guthrie, L.、Wilks, Y.、Aidinejad, H.(1991)。Subject-Dependent Co-Occurrence and Words Sense Disambiguation。California。146-152。  new window
6.Gonzalo, J.、Verdejo, Felisa、Chugur, I.、Cigarran, J.(1998)。Indexing with WordNet Synsets can Improve Text Retrieval。New Brunswick, NJ : ACL ; San francisco, CA。38-44。  new window
7.Gomez, F.(1998)。Linking WordNet Verb Classes to Semantic Interpretation。New Brunswick, NJ : ACL ; San francisco, CA。58-64。  new window
8.Farreres, X.、Gigau, G.、Rodriguez, H.(1998)。Using WordNet for Building WordNets。New Brunswick, NJ : ACL ; San francisco, CA。65-72。  new window
9.Luk, A. K.(1995)。Statistical Sense Disambiguation with Relatively Small Corpora using Dictionary Definitions181-188。  new window
10.Yarowsky, D.(1992)。Word-Sense Disambiguation Using Statistical Models of Roget’s Categories Trained on Large Corpora。Nantes, France。454-460。  new window
11.Yarowsky, D.(1995)。Unsupervised Word Sense Disambiguation Rivaling Supervised Methods189-196。  new window
12.陳信希、Lin, Chi-Ching、Lin, Wen-Cheng(2000)。Construction of a Chinese-English WordNet and its Application to CLIR。Hong Kong。189-196。  new window
學位論文
1.Resnik, Philip(1993)。Selection and Information: A Class-based Approach to Lexical Relationships(博士論文)。University of Pennsylvania。  new window
圖書
1.Fellbaum, Christiane(1998)。WordNet: An Electronic Lexical Database。MIT Press。  new window
2.Wang, Chi-Yung(2002)。Knowledge-based Sense Pruning using the HowNet: An Alternative to Word Sense Disambiguation。Thesis of Hong Kong University of Science andTechnology, Computer Science。  new window
3.Slator, B.(1991)。Using Context for Sense Preference。Lexical Acquistion: Exploiting On-line Resources to Build a Lexicon。Hillsdale, NJ。  new window
其他
1.Aslandogam, Y. A.，Their, C.，Yu, C. T.，Zou, J.，Rishe, N.(1997)。Using Semantic Contents and WordNet in Image Retrieval，Philadelphia。  new window
2.Atserias, J.，Climent, X.，Farreres, X.，Rigau, G.，Rodriguez, H.(1997)。Combining Multiple Methods for the Automatic Construction of Multilingual WordNets，Tzigov Chark, Glgaria。  new window
3.Carpuat, M.，Ngai, G.，Fung, P.，Church, Kenneth Ward(2002)。Creating a Bilingual Ontology: A Corpus-Based Approach for Aligning WordNet and HowNet，Mysore, India。  new window
4.Yang, C.，Ker, S. J.(2002)。Considerations of Linking WordNet with MRD。  new window
5.Riloff, Ellen，Jones, R.(1999)。Learning Dictionaries for Information Extraction by Multi-Level Bootstrapping。  new window
6.Ng, H. T.，Lee, H. B.(1996)。Integrating Multiple Knowledge Sources to Disambiguate Word Sense: An Exemplar-Based Approach，Santa Cruz, California, USA。  new window
7.Li, X.，Szpakowicz, S.，Matwin, S.(1995)。A WordNet-Based Algorithm for Word Semantic Sense Disambiguation，Montreal, Canada。  new window
8.Lee, C.，Lee, G.，Yun, S. J.(2000)。Automatic WordNet Mappign using Word Sense Disambiguation。  new window
9.Knight, K.，Luk, S. K.(1994)。Building a Large-scale Knowledge Base for Machine Translation，Seattle, WA, USA。  new window
10.Dorr, B. J.，Levow, G-A，Lin, D.，Thomas, S.(2000)。Chinese-English Semantic Resource Construction，Athens, Greece。  new window
11.Gale, W. A.，Church, Kenneth Ward，Yarowsky, D.(1992)。Using Bilingual Materials to Develop Word Sense Disambiguation Methods，Montreal。  new window
 
 
 
 
第一頁 上一頁 下一頁 最後一頁 top
QR Code
QRCODE

臺灣人文及社會科學引文索引資料庫

目前上線人數：933（臺灣：932，外國：1） ／ 本年度總使用人次：2096089 ／ 訪客人次（自102年09月）：67893976
國家圖書館著作權聲明 Copyright © 2013 All rights reserved.
本館地址: 100201臺北市中山南路20號． 本館地圖及交通資訊．
總機：(02)23619132．最佳瀏覽解析度為1024x768以上