請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/8896完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 鄭卜壬 | |
| dc.contributor.author | Chun-Bin Chu | en |
| dc.contributor.author | 朱崇賓 | zh_TW |
| dc.date.accessioned | 2021-05-20T20:03:36Z | - |
| dc.date.available | 2010-08-21 | |
| dc.date.available | 2021-05-20T20:03:36Z | - |
| dc.date.copyright | 2009-08-21 | |
| dc.date.issued | 2009 | |
| dc.date.submitted | 2009-08-18 | |
| dc.identifier.citation | [1] Nallapati, R., Feng, A., Peng, F., and Allan, J. Event threading within news topics. In CIKM04 conference proceedings, 446-453.(2004)
[2] Mei, Q. and Zhai, C.X. Discovering evolutionary theme patterns from text – an exploration of temporal text mining. In SIGKDD05 conference proceedings, 198-207.(2005) [3] Chien Chin Chen, Meng Chang Chen, TSCAN: A Novel Method for Topic Summarization and Content Anatomy, SIGIR2008 [4] N. Uramoto, K. Takeda, A method for realting multiple news-paper articles by using graph, Proceedings of 36th conference on Association for computational linguistics (1998). [5] NIST, Available at http://www.nist.gov, (2004). [6] M. Henzinger, B.-W. Chang, B. Milch and S. Brin, Query-free news search, Proceedings International WWW Conference, Budapest, Hungary (2003). [7] Allan, J., Carbonell, J., Doddington, G., Yamron, J., and Yang, Y. Topic detection and tracking pilot study: final report. In DARPA broadcast news transcription and understanding workshop proceedings, 194-218. (1998) [8] Chen, C. C., Chen, M. C., and Chen, M. S. 2005 LIPED: HMM-based Life Profiles for Adaptive Event Detection. In SIGKDD05 conference proceedings, 556-561. [9] Yang, Y., Pierce, T., and Carbonell, J. 1998. A study on retrospective and on-line event detection. In SIGIR98 conference proceedings, 28-36. [10] We. Ichiro, M. Hiroshi and K. Norio, Threading news video topics, Proc. of 5th ACM SIGMM International Workshop on Multimedia Information Retrieval (2003). [11] P. Duygulu, J.-Y. Pan and D.A. Forsyth, Towards auto-documentary: tracking the evolution of news stories, Proceedings of the ACM Multimedia Conference (2004). [12] H. Kozima, Text Segmentation Based on Similarity between Words, in Proceedings of the ACL, (1993). [13] M.A. Hearst, Multi-paragraph Segmentation of Expository Text, in Proceedings of the ACL, (1994). [14] Manoff & Shudson, 1986 [15] Cieri etal. 2002 | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/8896 | - |
| dc.description.abstract | 用事件流程圖的方式來理解新聞發展的來龍去脈,比直接去瀏覽整個相關新聞列表來的有效率且容易吸收.而要建立一個事件流程圖,我們必須先找出新聞事件之間的關係,才能將它們串接起來.
這篇論文提出了一個能夠自動偵測事件關係的方法.我們的方法是基於兩個事件的相似度來判斷它們是否具有前後關係.有別於單純的相似度運算,我們不只考慮到事件的主題,也考慮到事件中名稱實體所扮演的角色.在這篇論文中,主題是用來描述這個事件的輪廓,我們可以用主題來了解這個事件是在屬於哪一類型的新聞.而角色是代表一個命名實體在新聞事件中的行為,處境..等概念,即 代表一個實體在新聞事件中所扮演的角色. 這篇論文會介紹我們如何運用主題及角色的概念來偵測新聞事件的前後關係,以及做一些實驗來證明這個方法的可行性. | zh_TW |
| dc.description.abstract | Reading the evolution graph of news events is much easier than browsing the news events in a list. To construct the evolution graph, we have to detect the dependent relationship between news events.
In this paper we present a method to automatically detect the evolution of news events. Our method is based on the similarity between news events, our method considers not only the characteristic of news events, but also considers the roles played by entity names in news events. The characteristic of news events could be defined as the topic of these news events, we can roughly understand what happened about these news events by topic information. The role means the concept behind a name entity which describe the name entities’ behavior, situation…etc. The same entity name might play different roles in different news events. We will introduce how we use the role and topic information to detect the relationship between news events. | en |
| dc.description.provenance | Made available in DSpace on 2021-05-20T20:03:36Z (GMT). No. of bitstreams: 1 ntu-98-R96944038-1.pdf: 1169273 bytes, checksum: 05b7569c693a7e129a89d32e2f21a12e (MD5) Previous issue date: 2009 | en |
| dc.description.tableofcontents | 摘要 ii
Abstract iii Chapter 1 Introduction 1 1.1 Motivations 1 1.2 Previous Work 3 1.3 Problem Definition 4 1.4 Basic Idea 5 1.5 Challenges 6 1.6 Thesis Organization 7 Chapter 2 Relate Work 8 2.1 Topic Detection and Tracking (TDT) 8 2.2 Event Threading 10 Chapter 3 Model the News Article 12 3.1 Analysis of News Articles 12 3.2 Modeling the News Article 13 3.3 The Role 14 3.4 The Topic 21 3.5 Review of the Model 22 Chapter 4 Relationship Detection 24 4.1 Operations 24 4.2 Similarity between Documents 25 4.3 Role Similarity and Topic Similarity 29 4.4 Discussion 30 Chapter 5 Experiments 31 5.1 Overview 31 5.2 Dataset 32 5.3 Evaluation 33 5.4 Baseline 34 5.5 Experiment 1. Different Weight 35 5.6 Experiment 2: Window Size 43 5.7 Experiment 3: Different Feature Word 45 5.8 Experiment 4: Different Feature Size 46 Chapter 6 Conclusion and Future Work 48 6.1 Conclusion 48 6.2 Application 49 6.3 Future Work 50 | |
| dc.language.iso | en | |
| dc.title | 使用角色及主題資訊偵測新聞事件關係 | zh_TW |
| dc.title | News Event Relationship Detection Using Role and Topic information | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 97-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳信希,曾新穆,張嘉惠 | |
| dc.subject.keyword | 事件,關係,偵測, | zh_TW |
| dc.subject.keyword | Event,Detection,Relationship, | en |
| dc.relation.page | 52 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2009-08-18 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-98-1.pdf | 1.14 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。