跳到主要內容

臺灣博碩士論文加值系統

(3.237.38.244) 您好!臺灣時間:2021/07/26 09:05
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

: 
twitterline
研究生:林稚偉
研究生(外文):Chi-wei Lin
論文名稱:辨別問題分析之問題意圖於醫學問答之研究
論文名稱(外文):Identifying Question Intention in Question Analysis for Medical Question Answering
指導教授:盧文祥盧文祥引用關係
指導教授(外文):Wen-hsiang Lu
學位類別:碩士
校院名稱:國立成功大學
系所名稱:醫學資訊研究所
學門:醫藥衛生學門
學類:醫學技術及檢驗學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:67
中文關鍵詞:問題分析自然語言處理醫學問答系統答案萃取
外文關鍵詞:Answer ExtractionQuestion AnalysisMedical Question Answering SystemNatural Language Processing
相關次數:
  • 被引用被引用:2
  • 點閱點閱:223
  • 評分評分:
  • 下載下載:38
  • 收藏至我的研究室書目清單書目收藏:0
對一般使用者提出的醫學相關問題進行觀察和分析,我們發現大部分問題中都具有醫學關鍵詞和問題意圖,但由於使用者描述問題的方式和詞彙都不一樣,使用傳統關鍵詞比對來辨別問題意圖的效果並不好,因此我們提出利用問句中的意圖相關詞來辨別問題意圖。另外,我們也提出醫學關鍵詞的辨識方法找出使用者問句中具有代表性的醫學術語。
在答案萃取階段,利用搜尋引擎Google找到網路上能回答使用者問題的相關文件,藉由相似度計算挑選出問題相關的候選答案,並且利用我們提出的答案萃取的方法,考慮到兩個特徵:候選答案的距離和重要性來找出機率值最高的答案作為詞組層級答案。最後,透過不同層級答案的擴展,找出對應於使用者問題的詞組層級、句子層級和段落層級三種不同層級的答案提供使用者作參考。
從實驗結果可以得知,利用意圖相關詞的確能夠有效辨別問題意圖。在問題分析階段取得的醫學關鍵詞和問題意圖,能夠有效的找到問題相關的文件。在同樣的測試問題下,實驗的結果顯示我們的中文醫學問答系統比現有的問答系統 –answers.com's bb所得到的結果來的好。雖然我們目前的結果仍有很大的進步空間,不過就目前中文醫學專業資源不足的情況下,我們試著利用本論文提出的問題分析和答案萃取方法,搭配上既有的醫學資源,如MMODE、中英文雙語MeSH概念詞和我們定義的問題意圖,建構一個中文自然語言醫學問答系統,以解決一般中文使用者提出的醫學問題。
Observing and analyzing medical-related questions, we find that there should be an intention in most questions. But users use different description and terms to express the question, keyword matching is not effective to identify the question intention. So, we proposed that utilizing intention-related terms to identify the question intention. In addition, we proposed the method that can identify medical keywords in users’ questions.
In the document retrieval, we retrieve relevant documents in web with Google search engine. In the answer extraction, we will select possible candidate answers by calculating the similarity. Considering two features of answers:the distance feature and the importance feature, we choose the answer with the greatest probability as the phrase-level answer. After expanding answers in different levels, our system can provide corresponding answers of three levels: phrase level、sentence level and paragraph level answers for reference.
The experimental results show that using intention-related terms can effectively identify the question intention. Utilizing medical keywords and the question intention from question analysis can retrieve more relevant documents. All of all, under same testing questions, our proposed medical QA system can get better results than the existing QA system – answers.com's bb. Although our proposed methods are still much room for improvement, but under the current shortage of Chinese professional resources, we use our proposed methods and the existing medical resources, such as MMODE, concept terms of Bilingual MeSH, and the defined question intention to construct a Chinese Medical QA System for answering Chinese medical-related questions from general people.
摘要 III
Abstract V
誌謝 VII
章節目錄 VIII
表目錄 X
圖目錄 XI
1.序論 1
1.1研究動機與問題 1
1.2研究方法 4
1.3論文架構 6
2.相關研究與論文 7
2.1傳統問答(Factoid QA)相關研究 7
2.2醫學專業人事決策輔助相關研究 8
2.3醫學問答的研究 10
3.研究與方法 12
3.1研究問題與想法 12
3.1.1研究問題 12
3.1.2研究想法 13
3.2系統架構 14
3.2.1系統架構 14
3.2.2醫學問答機率模型 15
3.3問句分析(Question Analysis) 16
3.3.1醫學關鍵詞辨識 18
3.3.2意圖相關詞彙(Intention-related Terms) 22
3.3.3問題意圖辨別 25
3.4文件檢索(Document Retrieval) 27
3.5 答案萃取(Answers Extraction) 29
3.5.1候選答案萃取(Candidate Answers Extraction) 30
3.5.2 答案權重值計算(Answer Weighting ) 32
3.5.3 不同層級答案之擴展 34
4.實驗和評估 37
4.1實驗資料和評估準則 37
4.1.1實驗資料與實驗設計 37
4.1.2評估準則 38
4.2問題分析正確率之評估 39
4.2.1醫學關鍵詞辨識正確率之評估 39
4.2.2問題意圖辨別正確率之評估 41
4.3相關文件檢索效能評估 45
4.4答案萃取正確率之評估 46
4.4.1答案特徵函數之參數調校 46
4.4.2 不同答案萃取方法的效能評估 47
4.5不同層級答案正確率之評估 52
4.5.1句子層級答案正確率評估 52
4.5.2段落層級答案正確率評估 54
4.6不同問題分析方法之效能評估 56
4.7 不同系統之效能評估 59
5.結論與未來 63
5.1結論 63
5.2未來研究方向 64
參考文獻 65
附錄 A MeSH(Medical Subject Headings)的類別概述 68
M. W. Bilotti, P. Ogilvie, J. Callan, E. Nyberg 2007. Structured Retrieval for Question Answering. In Proceedings of SIGIR 2007: 351-358.
E. Brill, S. Dumais, Michele Banko 2002. An Analysis of the AskMSR Ques-tion-Answering System. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMLP), Philadelphia, July 2002, pages 257-264.
Y. Chen, M. Zhou, S. Wang 2006. Reranking Answers for Definitional QA Using Language Modeling. Proceedings of the 21st International Conference on Com-putational Linguistics and 44th Annual Meeting of the ACL, pages 1081–1088.
C. L. A. Clarke, G. V. Cormack, T. R. Lynam 2001. Exploiting Redundancy in Ques-tion Answering. In Proceedings of SIGIR 2001: 358-365.
J. Lafferty, A. McCallum, F. Pereira 2001.Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In Proceedings of the ICML.
J. Chu-Carroll, K. Czuba, J. Prager, A. Ittycheriah 2003. In Question Answering, Two Heads Are Better Than One. In Proceedings of HLT-NAACL: 24-31.
H. Cui, R. Sun, K. Li, M. Y. Kan, T. S. Chua 2005. Question Answering Passage Re-trieval Using Dependency Relations. In Proceedings of SIGIR 2005: 400-407.
D. Demner-Fushman, J. Lin 2006. Answer Extraction, Semantic Clustering, and Ex-tractive Summarization for Clinical Question Answering. Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL, pages 841–848.
S. Dumais, M. Banko, E. Brill, J. Lin, Andrew Ng 2002. Web Question Answering: Is More Always Better. In Proceedings of SIGIR 2002: 291-298.
H. Fang, C. Zhai 2006. Semantic Term Matching in Axiomatic Approaches to Infor-mation Retrieval. In Proceedings of SIGIR 2006: 115-122.
H. L. Hsu, W. S. Lu 2008, Utilizing Shallow Semantic Answer Inference Model for Medical Question Answering. The thesis of master.
J. Ko, T. Mitamura, E. Nyberg 2007. Language-independent Probabilistic Answer Ranking for Question Answering. Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 784–791.
J. Ko, L. Si, E. Nyberg 2007 A Probabilistic Graphical Model for Joint Answer Ranking in Question Answering. In Proceedings of SIGIR 2007: 343-350.
K. W. Kor, T. S. Chua 2007. Interesting Nuggets and Their Impact on Definitional Question Answering. In Proc. of SIGIR 2007: 335-342.
A. Korhonen, Y. Krymolowski, N. Collier 2006. Automatic Classification of Verbs in Biomedical Texts. Proceedings of the 21st International Conference on Computa-tional Linguistics and 44th Annual Meeting of the ACL, pages 345–352.
M. Lee, J. Cimino, H. R. Zhu, C. Sable, V. Shanker, J. Ely, H. Yu 2006. Beyond In-formation Retrieval—Medical Question Answering. AMIA 2006 Symposium Proceedings, pages 469-473.
J. Lin 2006. The Role of Information Retrieval in Answering Complex Questions. Proceedings of COLING/ACL Main Conference Poster Sessions, pages 523-530.
J. Lin and D. Demner-Fushman 2006. The Role of Knowledge in Conceptual Retrieval: A Study in the Domain of Clinical Medicine. In Proceedings of SIGIR 2006: 99-106.
J. Lin and B. Katz 2003. Question Answering from the Web using Knowledge Annota-tion and Knowledge Mining Techniques. In Proceedings of CIKM 2003: 116-122.
A. Moschitti, S. Quarteroni, R. Basili, S. Manandhar 2007. Exploiting Syntactic and Shallow Semantic Kernels for Question/Answer Classification. Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 776–783.
Y. Niu, X. Zhu, G. Hirst 2006. Using Outcome Polarity in Sentence Extraction for Medical Question-Answering. AMIA 2006 Symposium Proceedings, pages 599-603.
A. Novischi, D. Moldovan 2006. Question Answering with Lexical Chains Propagat-ing Verb Arguments. Proceedings of the 21st International Conference on Com-putational Linguistics and 44th Annual Meeting of the ACL, pages 897–904.
B. Ofoghi, J. Yearwood, R. Ghosh 2006. A Semantic Approach to Boost Passage Re-trieval Effectiveness for Question Answering. Proceedings of the 29th Australasian Computer Science Conference, Volume 48.
M. Paşca 2007. Lightweight Web-Based Fact Repositories for Textual Question Ans-wering. In Proceedings of CIKM 2007: 87-95.
J. Prager, P. Duboue, J. Chu-Carroll 2006. Improving QA Accuracy by Question In-version. Proceedings of the 21st International Conference on Computational Lin-guistics and 44th Annual Meeting of the ACL, pages 1073–1080.
S. L. Price, L. M. Delcambre, M. L. Nielsen 2006. Using Semantic Components to Express Clinical Questions Against Document Collections, In Proc. of HIKM 2006: 9-16.
G. Ramakrishnan, S. Chakrabarti, D. Paranjpe, P. Bhattacharyya 2004. Is Question Answering an Acquired Skill?, In Proceedings of WWW 2004: 111-120.
E. T. K. Sang, G. Bouma, and M. Rijke. 2005. Developing offline strategies for ans-wering medical questions, Proceedings of the 20th National Conference on Artifi-cial Intelligence (AAAI-05), pages 41–45
S. Tellex, B. Katz, J. Lin, A. Fernandes, and G. Marton 2003. Quantative Evaluation of Passage Retrieval Algorithms for Question Answering, In Proceedings of SIGIR 2003: 41-47.
M. Wu and T. Strzalkowski 2006. Utilizing Co-Occurrence of Answers in Question Answering. Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL, pages 1169–1176.
H. Yang, T. S. Chua, S. Wang, C. K. Koh 2003. Structured Use of External Know-ledge for Event-based Open Domain Question Answering, In Proceedings of SI-GIR 2003: 33-40.
H. Yu 2006. Towards Answering Biological Questions with Experimental Evidence: Automatically Identifying Text that Summarize Image Content in Full-Text Articles. AMIA 2006 Symposium Proceedings, pages 834-838.
W. Zhou, C. Yu, N. Smalheiser, V. Torvik, J. Hong 2007. Knowledge-intensive Con-ceptual Retrieval and Passage Extraction of Biomedical Literature. In Proceedings of SIGIR 2007: 655-662.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top