(3.238.7.202) 您好!臺灣時間:2021/03/04 21:39
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:::

我願授權國圖
: 
twitterline
研究生:肖湘
研究生(外文):Xiang Xiao
論文名稱:中文類比推理在語言樣式探勘中的應用研究
論文名稱(外文):Chinese Analogical Reasoning for Language Pattern Mining
指導教授:賴國華禹良治禹良治引用關係
指導教授(外文):K. Robert LaiLiang-Chih Yu
口試委員:常安
口試委員(外文):An Chang
口試日期:106年7月4日
學位類別:碩士
校院名稱:元智大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2017
畢業學年度:106
語文別:中文
論文頁數:45
中文關鍵詞:自然語言處理類比推理語言樣式詞向量
外文關鍵詞:Natural Language ProcessingAnalogical ReasoningLanguage PatternWord Embedding
相關次數:
  • 被引用被引用:0
  • 點閱點閱:89
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:2
類比推理是根據某類事物所具有的某種屬性,推測出類似事物也有相同屬性的推理方法。假設有四個物件a、b、a*、b*,類比推理是指a之於b的關係與a*之於b*的關係一致,表示為“a:b ::a*:b*”。如(“中國”,“北京”)和(“日本”,“東京”)之間存在類比的關係,即國家和首都,構成一組語言樣式(Language Pattern)。類比推理結合近年熱門的深度學習的詞向量模型,在自然語言處理領域產生了令人驚喜的效果。
隨著患抑鬱症人群的擴大,引發了社會各層的高度關注。負面生活事件是引發抑鬱情緒的重要原因,比如家庭成員的去世、與伴侶的爭吵、被老闆開除或被老師責備等。主語和負面生活事件的組合稱為負面生活事件語言樣式。因此能否通過自動準確地識別這些負面的生活事件語言樣式來理解那些有抑鬱傾向的網路文本對建立有效實用的精神病學網路服務是至關重要。
本研究針對負面生活事件語言樣式,分別應用超空間類比語言(Hyperspace Analog to Language, HAL)模型、簡單跳躍(Skip-gram)模型和連續詞袋(Continuous Bag-of-Words, CBOW)模型三種不同構造語義模型的方法,結合不同的類比推理算法進行語言樣式探勘實驗。研究主要可分為三個部分:1)對維基百科中文語料庫訓練出詞向量模型;2)從抑鬱症問答文本中人工挑选出潜在的負面生活事件語言樣式作为种子集,如(“父母”,“離婚”),並產生問題資料集;3)分別對不同的向量模型和不同的類比推理的方法組合進行負面生活事件語言樣式探勘的實驗。
Analogical reasoning is a reasoning method which based on a certain kind of thing has some kind of attribute, to speculate that similar things have the same attribute. Assuming that there are four objects: a, b, a*, b*, analogical reasoning means that the relationship between a and b is consistent with the relationship between a* and b*, expressed as "a: b :: a*: b*". For example, there are two pairs of words ("China", "Beijing") and ("Japan", "Tokyo"), there exists the analogical relationship between them, which is the state and the capital, constituting a language pattern. The combination of analogical reasoning and the popular deep learning word embedding models, has produced surprising results in the field of natural language processing.
With the expansion of the number of people suffering from depression, triggering a high degree of attention from all walks of life. Negative life events are an important reason of causing depression, such as the death of family members, quarrel with the spouse, fired by the boss or blamed by the teacher. The combination of a subject and a negative life event is called as a language pattern of negative life events. Therefore, whether it can through identify these negative life event language patterns automatically and accurately to understand those web text with depression trend, which is important to establish effective and practical psychiatric network services.
In this study, we focus on negative life event language patterns, applying three different language models which are Hyperspace Analog to Language model, Skip-gram model and the Continuous Bag-of-Words model respectively, to do the survey of language patterns analogical reasoning. The study can be divided into three parts: 1) training word embedding models with Wikipedia Chinese corpus; 2) finding out the existence of negative life event language patterns from the depression Q&A texts, such as ("parents", "divorce"), and then generate query data set; 3) combining different word representations and different methods of analogical reasoning to do experiments of negative life event language patterns mining with analogical reasoning.
摘要 v
ABSTRACT vii
誌 謝 ix
目錄 x
表目錄 xii
圖目錄 xiv
第一章、緒論 1
1.1 研究背景與意義 1
1.2 研究現狀 2
1.3 論文結構 5
第二章、詞向量與語言模型 7
2.1 詞向量 7
2.2 語言模型 8
2.2.1 CBOW模型 10
2.2.2 Skip-gram模型 11
2.2.3 Hyperspace Analog to Language模型 12
第三章、實驗總體架構 15
第四章、負面生活事件語言樣式 16
4.1 生成類比推理問題資料集 16
4.2 生成答案集 18
第五章、方法 20
5.1 樣式誘導:PPMI 20
5.2 樣式推論:類比方法 20
5.2.1 COSINE 21
5.2.2 COSMUL 21
5.2.3 HAL-Inference 22
第六章、實驗 23
6.1 實驗準備 23
6.1.1語料庫預處理 24
6.1.2 訓練詞向量模型 25
6.1.3 評估指標 27
6.2 語言樣式誘導實驗 28
6.3 語言樣式類比推理實驗 29
6.3.1 調參實驗 30
6.3.2 測試結果 33
第七章、總結與展望 40
參考資料 42
[1]Prade H, Richard G. A short introduction to computational trends in analogical reasoning[M]//Computational Approaches to Analogical Reasoning: Current Trends. Springer Berlin Heidelberg, 2014: 1-22.
[2]Toba H, Adriani M, Manurung R. Predicting Answer Location Using Shallow Semantic Analogical Reasoning in a Factoid Question Answering System[C]//26th Pacific Asia Conference on Language, Information and Computation (PACLIC 26). 2012: 246.
[3]Tu X, Feng D, Wang X J, et al. Analogical reasoning for answer ranking in social question answering[J]. IEEE Intelligent Systems, 2012, 27(5): 28-35.
[4]Chaudhri V K, Heymans S, Overholtzer A, et al. Large-Scale Analogical Reasoning[C]//AAAI. 2014: 359-365.
[5]Strannegård C, Nizamani A R, Persson U. Integrating Axiomatic and Analogical Reasoning[C]//International Conference on Artificial General Intelligence. Springer International Publishing, 2016: 181-191.
[6]Hug N, Prade H, Richard G. Experimenting Analogical Reasoning in Recommendation[C]//International Symposium on Methodologies for Intelligent Systems. Springer International Publishing, 2015: 69-78.
[7]Popov V, Hristova P. Automatic analogical reasoning underlies structural priming in comprehension of ambiguous sentences[C]//Proceedings of the 36th Annual Conference of the Cognitive Science Society. 2014: 1192-1197.
[8]Zheng Z, Wang Y, Lepage Y. Chinese word segmentation based on analogy and majority voting[J]. 2015.
[9]Gentner D, Namy L L. Analogical processes in language learning[J]. Current Directions in Psychological Science, 2006, 15(6): 297-301.
[10]Chien J T, Chen H Y. Mining of association patterns for language modeling.[C] INTERSPEECH 2004 - Icslp, International Conference on Spoken Language Processing, Jeju Island, Korea, October. 2004.
[11]Mendes A C, Antunes C. Pattern Mining with Natural Language Processing: An Exploratory Approach[M]// Machine Learning and Data Mining in Pattern Recognition. Springer Berlin Heidelberg, 2009:266-279.
[12]Recchia, G., & Jones, M. N. (2009). More data trumps smarter algorithms: Comparing pointwise mutual information with latent semantic analysis. Behavior research methods, 41(3), 647-656.
[13]Turney, P. (2001). Mining the web for synonyms: PMI-IR versus LSA on TOEFL. Machine Learning: ECML 2001, 491-502.
[14]Terra, E., & Clarke, C. L. (2003, May). Frequency estimates for statistical word similarity measures. In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology-Volume 1 (pp. 165-172). Association for Computational Linguistics.
[15]Van de Cruys, T. (2011, June). Two multivariate generalizations of pointwise mutual information. In Proceedings of the Workshop on Distributional Semantics and Compositionality (pp. 16-20). Association for Computational Linguistics.
[16]Turney P D. Similarity of semantic relations[J]. Computational Linguistics, 2006, 32(3): 379-416.
[17]Turney P D. Distributional semantics beyond words: Supervised learning of analogy and paraphrase[J]. arXiv preprint arXiv:1310.5042, 2013.
[18]Levy O, Goldberg Y, Dagan I. Improving distributional similarity with lessons learned from word embeddings[J]. Transactions of the Association for Computational Linguistics, 2015, 3: 211-225.
[19]Duc N T, Bollegala D, Ishizuka M. Using relational similarity between word pairs for latent relational search on the web[C]//Web Intelligence and Intelligent Agent Technology (WI-IAT), 2010 IEEE/WIC/ACM International Conference on. IEEE, 2010, 1: 196-199.
[20]Liang C, Lu Z. Chinese Analogy Search Considering Multi Relations[C]//Cloud and Service Computing (CSC), 2012 International Conference on. IEEE, 2012: 193-197.
[21]梁超, 呂釗, 顧君忠. 基於SVM的中文類比檢索方法[J]. 計算機科學, 2014, 41(5)111-115.
[22]Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space[J]. arXiv preprint arXiv1301.3781, 2013.
[23]Mikolov T, Sutskever I, Chen K, et al. Distributed representations of words and phrases and their compositionality[C]//Advances in neural information processing systems. 2013: 3111-3119.
[24]Levy O, Goldberg Y, Ramat-Gan I. Linguistic Regularities in Sparse and Explicit Word Representations[C]//CoNLL. 2014: 171-180.
[25]Qiu L, Zhang Y, Lu Y. Syntactic Dependencies and Distributed Word Representations for Chinese Analogy Detection and Mining[C]. EMNLP, 2015.
[26]Yu L C, Wu C H, Yeh J F, et al. HAL-Based Evolutionary Inference for Pattern Induction From Psychiatry Web Resources[J]. IEEE Transactions on Evolutionary Computation, 2008, 12(2):160-170.
[27]Yu L C, Chan C L, Wu C H, et al. Mining association language patterns for negative life event classification[C]//Proceedings of the ACL-IJCNLP 2009 Conference Short Papers. Association for Computational Linguistics, 2009: 201-204.
[28]Yu L C, Chan C L, Lin C C, et al. Mining association language patterns using a distributional semantic model for negative life event classification[J]. Journal of Biomedical Informatics, 2011, 44(4):509-518.
[29]Hinton, Geoffrey E. "Learning distributed representations of concepts." Proceedings of the eighth annual conference of the cognitive science society. Vol. 1. 1986.
[30]Xu, Wei, and Alexander I. Rudnicky. "Can artificial neural networks learn language models?." (2000).
[31]Bengio, Yoshua, et al. "Neural Probabilistic Language Models." Journal of Machine Learning Research 3.6(2003):1137-1155.
[32]Léon Bottou. Stochastic gradient learning in neural networks. In Proceedings of Neuro-Nımes, volume 91, 1991.
[33]Levy O, Goldberg Y. Dependency-Based Word Embeddings[C]//ACL (2). 2014: 302-308.
[34]Lund K, Burgess C. Producing high-dimensional semantic spaces from lexical co-occurrence[J]. Behavior Research Methods, Instruments, & Computers, 1996, 28(2) 203-208.
[35]Curt Burgess, Kay Livesay, Kevin Lund. Explorations in context space Words, sentences, discourse[J]. Discourse Processes, 1998, 25(2-3)211-257.
[36]中央研究院中文詞知識庫小組, http://ehownet.iis.sinica.edu.tw.
[37]http://opencc.byvoid.com/
[38]中央研究院中文詞知識庫小組, http://ckipsvr.iis.sinica.edu.tw/.
[39]Song D, Bruza P. Discovering information flow suing high dimensional conceptual space[C]// Research & Development in Information Retrieval. SIGIR '01 Proceedings of the 24th annual international ACM SIGIR conference on Research and developm, 2001:327-333.
[40]Song D, Bruza P D. Towards context sensitive information inference[J]. Journal of the Association for Information Science and Technology, 2003, 54(4):321–334.
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
系統版面圖檔 系統版面圖檔