請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/39545
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 劉長遠 | |
dc.contributor.author | Jau-Chi Huang | en |
dc.contributor.author | 黃昭綺 | zh_TW |
dc.date.accessioned | 2021-06-13T17:31:24Z | - |
dc.date.available | 2012-07-28 | |
dc.date.copyright | 2011-07-28 | |
dc.date.issued | 2011 | |
dc.date.submitted | 2011-07-08 | |
dc.identifier.citation | [1] Elman, J.L.: Finding structure in time. Cognitive Science 14, 179–211 (1990)
[2] Rumelhart, D.E.: Parallel distributed processing: Explorations. In McClelland, J.L.(eds.), The microstructure of cognition: Foundations. MIT Press, Cambridge, MA (1986) [3] Elman, J.L.: Distributed representations, simple recurrent networks, and grammaticalstructure. Machine Learning 7, 195–225 (1991) [4] Marcus, G.: Symposium on cognitive architecture: the algebraic mind. In Gernsbacher,M.A., Derry, S. (eds.), Proceedings of the 20th Annual Conference of the CognitiveScience Society, Mahway, NJ: Lawrence Erlbaum Associates (1998) [5] Elman, J.L.: Generalization, simple recurrent networks, and the emergence of structure.Proceedings of the 20th Annual Conf. of the Cognitive Science Society, Mahway, NJ(1998) [6] McCulloch, W., Pitts, W.: A logical calculus of the ideas immanent in nervous activity.Bull. Math. Biophys. 5, 115–133 (1943) [7] Siegelmann, H.T.: Computation beyond the turing limit. Science, 238(28), April 1995,632–637 (1995) [8] Cleeremans, A., Servan-Schreiber, D., McClelland, J.L.: Finite State Automata andSimple Recurrent Networks. Neural Computation 1, 372–381 (1989) [9] Altschul, S.F., Gish, W., Miller, W., Myers, E.W., Lipman, D.J.: Basic local alignmentsearch tool. J Mol Biol 215 (3), 403–410 (1990) [10] Altschul, S.F., Madden, T.L., Schaffer, A.A. et al.: Gapped BLAST and PSIBLAST: Anew generation of protein database search programs. Nucleic Acids Res. 25, 3389–3402(1997) [11] Macaya, G., Thiery, J.P., Bernardi, G.: An approach to the organization of eukaryoticgenomes at a macromolecular level. J. Mol. Biol. 108, 237–254 (1976) [12] Bernardi, G., et al.: The mosaic genome of warm-blooded vertebrates. Science 228, 953–957 (1985) [13] Bernardi, G.: The isochore organization of the human genome. Annu. Rev. Genet. 23,637–661 (1989) [14] Bernardi, G.: Isochores and the evolutionary genomics of vertebrates. Gene 241, 3–17(2000) [15] Bernardi, G.: Misunderstandings about isochores. Part 1. Gene 276, 3–13 (2001) [16] Clay, O., Carels, N., Douady, C., Macaya, G., Bernardi, G.: Compositional heterogeneitywithin and among isochores in mammalian genomes. I. CsCl and sequence analyses. Gene276, 15–24 (2001) [17] International Human Genome Sequencing Consortium, Initial sequencing and analysis ofthe human genome. Nature 409, 860–921 (2001) [18] Costantini, M., Clay, O., Auletta, F., Bernardi, G.: An isochore map of human chromosomes.Genome Res. 16, 536–541 (2006) [19] Fickett, J.W., Torney, D.C., Wolf, D.R.: Base compositional structure of genomes. Genomics13, 1056–1064 (1992) [20] Churchill, G.A.: Stochastic models for heterogeneous DNA sequences. Bull Math Biol.51, 79–94 (1989) [21] Churchill, G.A.: Hidden Markov chains and the analysis of genome structure. ComputChem. 16, 107–115 (1992) [22] Gu’eguen, L.: Sarment: python modules for HMM analysis and partitioning of sequences.Bioinformatics 21, 3427–3428 (2005) [23] Bernaola-Galv’an, P., Rom’an-Rold’an, R., Oliver, J.L.: Compositional segmentation andlong-range fractal correlations in DNA sequences. Phys Rev E. 53, 5181–5189 (1996) [24] Oliver, J.L., Rom’an-Rold’an, R., Perez, J., Bernaola-Galv’an, P.: SEGMENT: identifyingcompositional domains in DNA sequences. Bioinformatics 15, 974–979 (1999) [25] Oliver, J.L., Carpena, P., Hackenberg, M., Bernaola-Galv’an, P.: IsoFinder: computationalprediction of isochores in genome sequences. Nucleic Acids Res. 32, 287–292(2004) [26] Li, W.: Delineating relative homogeneous G+C domains in DNA sequences. Gene 276,57–72 (2001) [27] Li, W.: New stopping criteria for segmenting DNA sequences. Phys Rev Lett. 86, 5815–5818 (2001) [28] Li, W.: Are isochore sequences homogeneous? Gene 300, 129–139 (2002) [29] Cohen, N., Dagan, T., Stone, L., Graur, D.: GC composition of the human genome: insearch of isochores. Mol Biol Evol. 22, 1260–1272 (2005) [30] Husmeier, D., Wright, F.: A Bayesian approach to discriminate between alternative DNAsequence segmentations. Bioinformatics 18, 226–234 (2002) [31] Boys, R.J., Henderson, D.A.: A Bayesian approach to DNA sequence segmentation.Biometrics 60, 573–581 (2004) [32] Haiminen, N., Mannila, H.: Discovering isochores by leastsquares optimal segmentation.Gene 394, 53–60 (2007) [33] Chomsky, N.: Three models for the description of language. IRE Transactions on InformationTheory 2, 113–124 (1956) [34] Lee, T.B., Hendler, J., Lassila, O.: The semantic web. Scientific American (2001) [35] Uschold, M., Gruninger, M.: Ontologies: Principles, methods and applications. TheKnowledge Engineering Review 11(2), 93–136 (1996) [36] Lowe, W.: Towards a theory of semantic space. In Proceedings of the 23rd AnnualConference of the Cognitive Science Society, pp. 576–581, Edinburgh, UK (2001) [37] Lowe, W., McDonald, S.: The direct route: Mediated priming in semantic space. InProceedings of the 22nd Annual Conference of the Cognitive Science Society, pp. 675–680, Philadelphia, PA (2000) [38] McDonald, S.: Environmental Determinants of Lexical Processing Effort. Ph.D. thesis,University of Edinburgh (2000) [39] Levy, J.P., Bullinaria, J.A.: Learning lexical properties from word usage patterns. InRobert M. French and Jacques P. Sougn’e editors, Connectionist Models of Learning,Development, and Evolution, pp. 273–282, Springer (2001) [40] Lund, K., Burgess, C., Atchley, R.A.: Semantic and associative priming in highdimensionalsemantic space. In Proceedings of the 17th Annual Conference of the CognitiveScience Society. Mahwah, NJ: Lawrence Erlbaum Associates (1995) [41] Harris, Z.S.: Mathematical Structures of Language. Wiley, New York (1968) [42] Grefenstette, G.: Explorations in Automatic Thesaurus Discovery. Kluwer AcademicPublishers, Dordrecht (1994) [43] Lin, D.: Automatic retrieval and clustering of similar words. In Proceedings of the JointAnnual Meeting of the Association for Computational Linguistics and International Conferenceon Computational Linguistics, pp. 768–774, Montr’eal, Canada (1998) [44] Marra, M.A., Jones, S.J.M., Astell, C.R., et al.: The genome sequence of the SARSassociatedcoronavirus. Science 300, 1399–1404 (2003) [45] Ksiazek, T.G., Erdman, D., Goldsmith, C.S., et al.: A novel coronavirus associated withsevere acute respiratory syndrome. The New England Journal of Medicine. 348, 1953–1966 (2003) [46] Peiris, J.S., Lai, S.T., Poon, L.L., et al.: Coronavirus as a possible cause of severe acuterespiratory syndrome. 361(9366), 1319–1325 (2003) [47] Drosten, C., G‥uther, S., Preiser, W., et al.: Identification of a novel coronavirus inpatients with severe acute respiratory syndrome. The New England Journal of Medicine.348, 1967–1976 (2003) [48] Benson, D.A., Karsch-Mizrachi, I., Lipman, D.J., Ostell, J., Wheeler, D.L.: GenBank.Nucleic acids research 33, D34–D38 (2005) [49] Liou, C.-Y., Huang, J.-C., Yang, W.-C.: Semantic addressable encoding. In: ICONIP,The 13th International Conference on Neural Information Processing, October 3-6 2006.LNCS, vol. 4232, pp. 183–192. Springer, Heidelberg (2006) [50] Liou, C.-Y., Huang, J.-C., Yang, W.-C.: Modeling word perception using the Elmannetwork. Neurocomputing 71, 3150–3157 (2008) [51] Huang, J.-C., Cheng, W.-C., Liou, C.-Y.: Distributed representation of word. In: ACIIDS,April. 20-22, Daegu city, Korea. LNAI 6591, pp. 169–176. (2011) [52] Shi, X.H., Liang, Y.C., Lee, H.P., Lin, W.Z., Xu, X., Lim, S.P.: Improved Elman networksand applications for controlling ultrasonic motors. Appl Artif Intel 18(7), 603–29(2004) [53] Attneave, F.: Informational aspects of visual perception. Psychol. Rev. 61, 183–193(1954) [54] Barlow, H.B.: Unsupervised learning. Neural Comp. 1, 295–311 (1989) [55] Barlow, H. B., Kaushal, T. P. and Mitchison, G. J.: Finding minimum entropy codes.Neural Computation 1, 412–423 (1989) [56] Burrows, J.: Questions of authorship: attribution and beyond. A lecture delivered onthe occasion of the Roberto Busa Award, ACH-ALLC 2001 New York, Computers andthe Humanities 37, 5–32 (2003) [57] Holmes, D.I.: The evolution of stylometry in humanities scholarship. Literary and LinguisticComputing 13, 111–117 (1998) [58] Tweedie, F.J., Baayen, R.H.: How variable may a constant be measures of lexical richnessin perspective? Computers and the Humanities 32, 323–352 (1998) [59] William, C.B.: Mendenhall’s studies of word-length distribution in the works of Shakespeareand Bacon, Biometrika 62, 207–212 (1975) [60] Yang, A.C.-C., Peng, C.-K., Yien, H.-W., Goldberger, A.L.: Information categorizationapproach to literary authorship disputes. Physica A-Statistical Mechanics and ItsApplications 329, 473–483 (2003) [61] Yoshida, N., Kiyoki, Y., Kitagawa, T.: An associative search method based on symbolicfiltering and semantic ordering for database systems. Proc. of 7th IFIP 2.6 Working Conf.on Database Semantics (DS-7) in Leysin, Switzerland, 215–237(1997) [62] Frakes, W.B.: Stemming algorithms, information retrieval: data structures and algorithms,Frakes, W.B., Ricardo, B.-Y. (eds.), Englewood Cliffs, NJ, Prentice-Hall, 131–160(1992) [63] Porter, M.F.: An algorithm for suffix stripping. Program, 14, 130–137 (1980) [64] Felsenstein, J.: PHYLIP (Phylogeny Inference Package) version 3.5c [Program], Departmentof Genetics, University of Washington, Seattle (1993) [65] Huffman, D.A.: A method for the construction of minimum-redundancy codes. Proceedingsof the Institute of Radio Engineers 40, 1098–1102 (1952) [66] Saitou N., Nei, M.: The neighbor-joining method: A new method for reconstructingphylogenetic trees. Molecular Biology and Evolution 4, 406–425 (1987) [67] Mallery, J.C.: Thinking about foreign policy: Finding an appropriate role for artificial intelligencecomputers. Ph.D. dissertation. MIT Political Science Department, Cambridge,MA. (1988) [68] Turing, A.M.: Computing machinery and intelligence. Mind 54, 443–460 (1950) [69] Navigli, R.: Word sense disambiguation:a survey. ACM Computing Surveys, 41(2), 1–69(2009) [70] Rivest, R.L.: Learning decision lists. Mach. Learn. 2, 3, 229–246 (1987) [71] Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers.In Proceedings of the 5th Annual Workshop on Computational Learning Theory(Pittsburgh, PA) 144–152 (1992) [72] Schutze, H.: Automatic word sense discrimination. Computat. Ling. 24, 1, 97–124 (1998) [73] Bloom, H.: Shakespeare: The invention of human. Riverhead Books, New York, (1998) [74] Honigmann, E.A.J.: Shakespeare’s Impact on his Contemporaries (1982) [75] McEnery, T., Oakes, M.: Authorship identification and computational stylometry. Handbookof Natural Language Processing, Marcel Dekker, Inc. 545–562 (2000) [76] Burns, Edward (ed.) King Henry VI, Part 1. The Arden Shakespeare, 3rd Series; London:Arden (2000) | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/39545 | - |
dc.description.abstract | 簡單遞迴網路具有找出序列資料中內藏結構的能力。本篇論文使用簡單遞迴網路來處理基因序列,利用網路預測錯誤高的地方找出蛋白質編碼區域的交界處。另外本篇論文提出一個新的演算法,讓在訓練簡單遞迴網路的時候不僅去改變其權重值還去改變輸入的編碼方式以降低預測錯誤。透過這樣的方式所得到的編碼具有文義編碼的特性,並將其運用在語意搜尋、作者寫作風格分析和詞義消歧上。 | zh_TW |
dc.description.abstract | Elman network can discover the hidden structure of sequential data. This thesis uses Elman network to process the genome sequence and detects the boundary of the protein coding region according to the prediction error. Moreover, for literal works analysis, it proposes a redesigned Elman network training algorithm to renew the distributed representation in each iteration. The representation will possess the form-based and function-based similarity in certain degree and is used to do semantic search, writing stylish analysis, and solve word sense disambiguation. | en |
dc.description.provenance | Made available in DSpace on 2021-06-13T17:31:24Z (GMT). No. of bitstreams: 1 ntu-100-D93922017-1.pdf: 4573872 bytes, checksum: cc142aa8bed9076259c77cea60404687 (MD5) Previous issue date: 2011 | en |
dc.description.tableofcontents | 1 Background 11
1.1 Elman network 11 1.2 Discovering the underlying structure of word 13 1.2.1 Artificial simple sentence generator 14 1.2.2 Experiment setting 15 1.2.3 Experiment result 15 1.3 Discovering lexical classes from word order 18 1.4 Applications 20 1.4.1 Segmentation 20 1.4.2 Semantic encoding 22 2 Finding hidden structure from DNA sequences 25 2.1 Method 25 2.2 Experiments 26 2.2.1 Data description 26 2.2.2 Experiment setting 26 2.2.3 Experiment result 27 2.3 Discussion 30 3 Redesign Elman network training algorithm 34 3.1 Iterative re-encoding 34 3.2 Normalization 35 3.3 Experiments 37 3.3.1 Data description 37 3.3.2 Experiment setting 37 3.3.3 Experiment result 38 3.4 Disscusion 41 4 Semantic encoding 42 4.1 Distributed representation of word 42 4.2 Minimum entropy coding 47 4.3 Semantic search 52 4.3.1 Multidimensional scaling (MDS) space 53 4.3.2 Representative vector of a whole document 54 4.3.3 Relation comparison 54 4.3.4 Example of literature categorization 55 5 Coding for polysemous words 58 5.1 Multi-meaning re-encoding 62 5.2 Evolution of writing style 66 5.3 Example of literature similarity 67 5.4 Multi-code for a single word 70 5.4.1 Iterative multi-code re-encoding 73 5.4.2 Experiment 74 5.4.3 Discussion 75 6 Conclusion and Future Work 80 | |
dc.language.iso | en | |
dc.title | 簡單遞迴網路解析序列符號內藏結構與文義編碼 | zh_TW |
dc.title | Finding hidden structure and semantic encoding from sequential symbols by Elman network | en |
dc.type | Thesis | |
dc.date.schoolyear | 99-2 | |
dc.description.degree | 博士 | |
dc.contributor.oralexamcommittee | 王家祥,呂育道,趙坤茂,吳建銘,林軒田 | |
dc.subject.keyword | 簡單遞迴網路,基因序列,分段,文義編碼,語意搜尋,詞義消歧, | zh_TW |
dc.subject.keyword | Elman network,DNA segmentation,semantic encoding,writing stylish analysis,word sense disambiguation, | en |
dc.relation.page | 89 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2011-07-08 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-100-1.pdf 目前未授權公開取用 | 4.47 MB | Adobe PDF |
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。