thesis/reference.bib

   1 @Preamble{"\eject\addcontentsline{toc}{chapter}{\bibname}"}
   2 %CMU-CS-96-143.ps
   3 @PhdThesis{Ravishankar,
   4   author =       {Mosur K. Ravishankar},
   5   title =        {Efficient Algorithms for Speech Recognition},
   6   school =       {Carnegie Mellon University},
   7   year =         1996
   8 }
   9
  10 %oflazer96errortolerant
  11 @article{Oflazer,
  12   author =       {Kemal Oflazer},
  13   title =        {Error-tolerant Finite-state Recognition with Applications to
  14                   Morphological Analysis and Spelling Correction},
  15   journal =      "CL",
  16   volume =       22,
  17   number =       1,
  18   pages =        {73-89},
  19   year =         1996,
  20   url =          {http://www.aclweb.org/anthology/J96-1003.pdf}
  21 }
  22
  23 %Ha-03.pdf
  24 @Article{LAH,
  25   author =       {Le An Ha},
  26   title =        {A method for word segmentation in Vietnamese},
  27   journal =      {},
  28   year =         {}
  29 }
  30
  31 %a-new-approach-for.ps
  32 @Article{Chang,
  33    title =        "A New Approach for Automatic Chinese Spelling
  34                   Correction",
  35    author =       "Chao-Huang Chang",
  36    year =         "1998",
  37    month =        mar # "~01",
  38 }
  39
  40 %J96-3004.pdf
  41 @article{Sproat,
  42   author =       {Richard W Sproat and Chilin Shih and William Gale and Nancy Chang},
  43   title =        {A Stochastic Finite-State Word-Segmentation Algorithm for
  44                   {Chinese}},
  45   journal =      "CL",
  46   volume =       22,
  47   number =       3,
  48   pages =        {377-404},
  49   year =         1996,
  50   url =          {http://www.aclweb.org/anthology/J96-3004.pdf}
  51 }
  52
  53
  54 @Article{Chunyu,
  55   author =       {Chunyu Kit and Zhiming Xu and Jonathan J.Webster},
  56   title =        {Integrating Ngram Model and Case-based Learning For Chinese Word Segmentation},
  57   journal =      {},
  58   year =         {},
  59 }
  60
  61 %mlwordsigir.ps
  62 @Article{softcount,
  63    title =        "Discovering Chinese Words from Unsegmented Text",
  64    author =       "A Pratt and Padhraic Smyth and Xianping Ge",
  65    year =         "1999",
  66    month =        aug # "~22",
  67 }
  68
  69 %icassp00.pdf
  70 @Article{text-tiling,
  71    author =       "Hai-Feng Wang and Jianfeng Gao and Kai-Fu Lee and
  72                   Mingjing Li Li",
  73    title =        "A unified approach to statistical language modeling
  74                   for Chinese",
  75    institution =  "Microsoft Research (MSR)",
  76    year =         "2000",
  77    month =        jun,
  78 }
  79
  80 %paper2.pdf
  81 @Article{,
  82   author =       {Nianwen Xue},
  83   title =        {Chinese Word Segmentation as Character Tagging},
  84   journal =      {},
  85   year =         {},
  86 }
  87
  88 %IDA01.pdf
  89 @Article{self-supervised,
  90    author =       "Fuchun Peng and Dale Schuurmans",
  91    title =        "Self-Supervised {Chinese} Word Segmentation",
  92    journal =      "Lecture Notes in Computer Science",
  93    volume =       "2189",
  94    pages =        "238--242",
  95    year =         "2001",
  96    CODEN =        "LNCSD9",
  97    ISSN =         "0302-9743",
  98    bibdate =      "Sat Feb 2 13:06:32 MST 2002",
  99 }
 100
 101 @Article{soundex,
 102   author =       {K. Kukich},
 103   title =        {Techniques for Automatically Correcting Words in Text},
 104   journal =      {ACM Computing Surveys},
 105   year =         {1992},
 106 }
 107
 108
 109
 110 @Article{Damerau,
 111   author =       {F. J. Damerau},
 112   title =        {A technique for computer detection and correction of
 113                   spelling errors.},
 114   journal =      {Communications of the Association for Computing Machinery},
 115   year =         1964,
 116   volume =       7,
 117   number =       3,
 118   pages =        {171-176},
 119 }
 120
 121 %lucchesi92applications.ps.gz
 122 @TechReport{LuKo91,
 123    author =       "C. L. Lucchesi and T. Kowaltowski",
 124    title =        "Applications of finite automata representing large
 125                   vocabularies",
 126    institution =  "Instituto de Matem{\'a}tica, Universidade Estadual de
 127                   Campinas",
 128    year =         "1991",
 129    type =         "Relat{\'o}rio T{\'e}cnico",
 130    number =       "9/91",
 131    address =      "S{\~a}o Paulo, Brasil",
 132    owner =        "zimmerma",
 133    keywords =     "spell",
 134 }
 135
 136
 137 @Article{oai:CiteSeerPSU:222471,
 138    title =        "Segmenting Korean Compound Nouns using Statistical
 139                   Information and a Preference Rule",
 140    author =       "Bo-hyun Yun and Hae-chang Rim and Min-jeung Cho",
 141    year =         "1970",
 142    month =        jan # "~01",
 143 }
 144
 145 @Comment \bibitem{phonetex}. {\em
 146 @Comment   }
 147 %an-evaluation-of-phonetic.ps.gz
 148 @Article{phonetex,
 149    title =        "An Evaluation of Phonetic Spell Checkers",
 150    author =       "Jim Austin and Victoria J. Hodge and Yo Dd",
 151    year =         "2001",
 152    month =        nov # "~21",
 153 }
 154
 155 @Comment \bibitem{}Bo-Hyun Yun, Min-Jeung Cho, Hae-Chang Rim. {\em Segmenting Korean
 156 @Comment   Compound Nouns using Statistical Information and a Preference
 157 @Comment   Rule. }%PACLING97.ps
 158 @Comment \bibitem{}Roger I. W. Spooner and Alistair D. N. Edwards. {\em User
 159 @Comment   Modelling for Error Recovery: A Spelling Checker for Dyslexic
 160 @Comment   Users}%spooner97user.ps.gz
 161 @Comment \bibitem{}Justin Zobel and Philip Dart. {\em Finding Approximate Matches in
 162 @Comment   Large Lexicons.}%zobel95finding.ps.gz
 163 @Comment \bibitem{}Sun Maosong, Shen Dayang, Huang Changning. {\em CSeg\&Tag1.0: A
 164 @Comment   Practical Word Segmenter and POS Tagger for Chinese Texts.}%A97-1018.pdf
 165 @Comment \bibitem{wordseg}Đinh Điền, Hoàng Kiếm, Nguyễn Văn Toàn. {\em Vietnamese Word
 166 @Comment   Segmentation.}%0047-02.pdf
 167 @Comment \bibitem{}Bidyut Baran Chaudhuri. {\em Reversed word dictionary and
 168 @Comment   phonetically similar word grouping based spell-checker to Bangla
 169 @Comment   text.}%bangla.pdf
 170 @Comment \bibitem{}Timothy Gambell, Charles D. Yang. {\em Scope and Limits of
 171 @Comment   Statistical Learning in Word Segmentation.}%gambell_yang.pdf
 172 @comment Mostly unsupervised statistical segmentation of japananese: applications to kainji %segment.pdf
 173
 174 %ICCC-2001.pdf
 175 @Article{iccc,
 176    author =       "Andi Wu and George Heidorn and Zixin Jiang and Terence
 177                   Peng",
 178    title =        "Correction of Erroneous Characters in Chinese Sentence
 179                   Analysis",
 180    institution =  "Microsoft Research (MSR)",
 181    publisher =    "Chinese and Oriental Language Information Processing
 182                   Society",
 183    year =         "2001",
 184    month =        dec,
 185 }
 186
 187 @Comment \bibitem{}Fuchun Peng, Xiangji Huang, Dale Schuurmans, Shaojun
 188 @Comment   Wang. {\em Text Clasification in Asian Languages without Word
 189 @Comment   Segmentation.}%IRAL2003.pdf
 190 @Comment \bibitem{}Yalin Wang, Ihsin T. Phillips, Robert
 191 @Comment   Haralick. {\em Statistical-based Approach to Word Segmentation.}%wordicpr.pdf
 192 @Comment \bibitem{}{\em Combining Syntactical And Statistical Language Constraints
 193 @Comment   in Context-dependent Language Models for Interactive Speech
 194 @Comment   Applications.}%K026.pdf
 195
 196
 197
 198 @Book{LoiChinhTa,
 199   author =       {TS. Lê Trung Hoa},
 200   title =        {Lỗi chính tả và cách khắc phục},
 201   publisher =    {NXB Khoa học Xã hội},
 202   year =         2002
 203 }
 204
 205
 206
 207 @Book{,
 208   author =       {PGS. Hồ Lê and TS. Trần Thị Ngọc Lang and Tô Đình Nghĩa},
 209   title =        {Lỗi từ vựng và cách khắc phục},
 210   publisher =    {NXB Khoa học Xã hội},
 211   year =         2002,
 212 }
 213
 214 @Article{Tuoi,
 215   author =       {PTS. Phan Thị Tươi and KS. Nguyễn Hứa Phùng and
 216                   KS. Huỳnh Vụ Như Liên and KS. Phạm Quyết Thắng},
 217   title =        {Bắt lỗi chính tả tự động cho tiếng Việt bằng máy tính},
 218   journal =      {Đề tài nghiên cứu khoa học Sở Khoa học Công nghệ và Môi trường},
 219   year =         {1998},
 220 }
 221
 222 @Article{worddef,
 223   author =       {Đinh Điền},
 224   title =        {Từ tiếng Việt},
 225   year =         2000,
 226   institution =  "VNU-HCMC"
 227 }
 228
 229 @Article{Golding95,
 230   author =       {Andrew R. Golding},
 231   title =        {A Bayesian hybrid method for context-sensitive spelling correction},
 232   journal =      {Proceedings of the Third Workshop on Very Large Corpora},
 233   year =         {1995},
 234   pages =        {39-53},
 235 }
 236
 237
 238
 239 @Article{Golding99,
 240   author =       {Andrew R. Golding and Dan Roth},
 241   title =        {A Winnow-based approach to context-sensitive correction},
 242   journal =      {Machine Learning, Special issue on Machine Learning and Natural Language Processing},
 243   year =         1999,
 244   volume =       34,
 245   pages =        {107-130}
 246 }
 247
 248
 249
 250 @Article{Golding96,
 251   author =       {Andrew R. Golding and Yves Schabes},
 252   title =        {Combining trigram-based and feature-based methods for context-sensitive spelling correction},
 253   journal =      {Proceedings of the 34th Annual Meeting of the Association for Computational Linguistics},
 254   year =         1996
 255 }
 256
 257 @Article{McIlroy,
 258   author =       {M. Douglas McIlroy},
 259   title =        {Development of a spelling list},
 260   journal =      {IEEE Transactions on Communications},
 261   year =         1982,
 262   volume =       {COM-30},
 263   number =       {1.1},
 264   pages =        {91-99}
 265 }
 266
 267 @Article{Peterson,
 268   author =       {James Lyle Peterson},
 269   title =        {Computer programs for detecting and correcting spelling errors},
 270   journal =      {Communications of the Association of Computing Machinery},
 271   year =         1980,
 272   volume =       23,
 273   number =       12,
 274   pages =        {676-687}
 275 }
 276
 277 @Article{Agirre,
 278   author =       {Eneko Agirre and Koldo Gojenola and Kepa Sarasola
 279                   and Atro Voutilainen},
 280   title =        {Towards a single proposal in spelling correction},
 281   journal =      {COLING-ACL '98, 36th Annual Meeting of the
 282                   Association for Computational Linguistics and 17th
 283                   International Conference on Computational Linguistics},
 284   year =         1998,
 285   pages =        {463-463}
 286 }
 287
 288 @Book{Petersonb,
 289    author =       "James Lyle Peterson",
 290    title =        "Computer Programs For Spelling Correction",
 291    publisher =    "Spring{\-}er-Ver{\-}lag, Inc.",
 292    address =      "Berlin, Germany~/ Heidelberg, Germany~/ London, UK~/
 293                   etc.",
 294    pages =        "vi + 213",
 295    year =         "1980",
 296    ISBN =         "3-540-10259-0",
 297    LCCN =         "QA76.6 .P474",
 298    bibdate =      "Tue Jul 26 10:30:05 1994",
 299 }
 300
 301 @Article{Rada,
 302   author =       {R. Rada and H. Mili and E. Bicknell and M. Blettner},
 303   title =        {Development an Application of a Metric on Semantic Nets},
 304   journal =      {IEEE Transactions on Systems, Man and Cybernetics},
 305   year =         1989,
 306   volume =       19,
 307   number =       1,
 308   pages =        {17-30}
 309 }
 310
 311 @Article{ChenLiu,
 312   author =       {K. J. Chen and S. H. Liu},
 313   title =        {Word Identification for Madarin Chinese sentences},
 314   journal =      {Proceedings of the Fifthteenth International Conference for Computational Linguistics},
 315   year =         1992
 316 }
 317
 318 %cws-ACL03.pdf
 319 @Article{sc,
 320   author =       {Jianfeng Gao and Mu Li and  Chang-Ning Huang},
 321   title =        {Improved Source-Channel Models for Chinese Word Segmentation},
 322   journal =      {},
 323   year =         2003
 324 }
 325
 326 @Article{tbl,
 327   author =       {Lidia Mangu and Eric Brill},
 328   title =        {Automatic Rule Acquisition for Spelling Correction},
 329   journal =      {},
 330   year =         1997
 331 }
 332
 333 @Article{palmer,
 334   author =       {David Palmer},
 335   title =        {A Trainable Rule-Based Algorithm for Word Segmentation},
 336   journal =      {Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics},
 337   year =         1997
 338 }
 339
 340 %0047-02.pdf
 341 @Article{wordseg,
 342   author =       {Dinh Dien and Hoang Kiem and Nguyen Van Toan},
 343   title =        {Vietnamese Word Segmentation},
 344   journal =      {},
 345   year =         2002
 346 }
 347
 348 @Book{knuth73,
 349   author =       {D. E. Knuth},
 350   title =        {The Art of Computer Programming. Vol. 3: Sorting and Searching},
 351   publisher =    {Addison Wesley},
 352   year =         1973
 353 }
 354
 355 @Article{hhmm,
 356   author =       {Shai Fine and Yoram Singer and Naftali Tishby},
 357   title =        {A Hierarchical Hidden Markov Model: Analysis and Applications},
 358   journal =      {Machine Learning},
 359   year =         1998,
 360   pages =        {32-41}
 361 }
 362
 363 %W03-1709.pdf
 364 @Article{hhmm2,
 365   author =       {Hua-Ping Zhang and Qun Liu and Xue-Qi Cheng and Hao Zhang and Hong-Kui Yu},
 366   title =        {Chinese Lexical Analysis Using Hierarchical Hidden Markov Model},
 367   journal =      {},
 368   year =         2003
 369 }
 370
 371 @Book{cg,
 372   author =       {F. Larlsson and A. Voutilainen and J. Heikkila and A. Anttila},
 373   title =        {Constraint Grammar: a Language-Independant System for Parsing Unrestricted text},
 374   publisher =    {Berlin and New York: Mouton de Gruyter},
 375   year =         1994,
 376 }
 377
 378 @Article{Tachtu,
 379   author =       {Dinh Dien and Hoang Kiem and Nguyen Van Toan},
 380   title =        {Vietnamese word segmentation},
 381   journal =      {NLPRS},
 382   year =         {2001},
 383   month =        {11}
 384 }
 385
 386
 387 @Article{tsdx,
 388   author =       {Theppitak Karoonboonyanan and Virach Sornlertlamvanich and Surapant Meknavin},
 389   title =        {A Thai Soundex System for Spelling Correction},
 390   journal =      {Proceedings of the National Language Processing Pacific Rim Symposium},
 391   year =         {1997},
 392 }
 393
 394 @Article{vietdecisionlist,
 395   author =       {Nguyễn Phương Thái and Nguyễn Quốc Toản and Lê Văn Cường and Nguyễn Văn Vinh},
 396   title =        {Kiểm lỗi chính tả tiếng Việt sử dụng danh sách quyết định},
 397   journal =      {},
 398   year =         {2002},
 399 }
 400
 401 @Article{srilm,
 402   author =       {Andreas Stolcke},
 403   title =        {SRILM - An Extensible Language Modeling Toolkit},
 404   journal =      {Proc. Intl. Conf. Spoken Language Processing, Denver, Colorado},
 405   year =         {2002},
 406   month =        {9},
 407 }
 408
 409
 410
 411 @Article{smt,
 412   author =       {Đinh Điền and Nguyễn Thống Nhất and Nguyễn Thái Ngọc Duy},
 413   title =        {Cách tiếp cận thống kê cho hệ dịch tự động Việt-Anh},
 414   journal =      {Tạp chí phát triển KHCN},
 415   year =         2003,
 416   volume =       6,
 417   pages =        {27-33}
 418 }
 419
 420 @Article{grcheck,
 421   author =       {Nguyễn Đức Hải and Nguyễn Phạm Hải Nhi},
 422   title =        {Phân tích cú pháp tiếng Việt và bắt lỗi chính tả},
 423   journal =      {Luận văn Cử nhân Tin học. ĐH Khoa học Tự nhiên HCM},
 424   year =         1999
 425 }
 426
 427 @Article{Tachtu2,
 428   author =       {Nguyễn Văn Toàn and Nguyễn Thị Minh Hằng},
 429   title =        {Tách từ tiếng Việt},
 430   journal =      {Luận văn Cử nhân Tin học. ĐH Khoa học Tự nhiên HCM},
 431   year =         2001
 432 }
 433
 434 @Article{wordnetviet,
 435   author =       {Nguyễn Văn Toàn and Văn Chí Nam and Nguyễn Thái Ngọc Duy},
 436   title =        {Xây dựng {WordNet} tiếng Việt},
 437   journal =      {Hội thảo quốc gia lần 6. Một số vấn đề CNTT, truyền thông, chủ để xử lý ngôn ngữ},
 438   year =         2003
 439 }
 440