(100.26.179.251) 您好!臺灣時間:2021/04/14 06:15
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:吳毓傑
研究生(外文):Yu-Chieh Wu
論文名稱:結合頂層與底層句法資訊之中文詞相依性分析
論文名稱(外文):Incorporating top-level and bottom-level information for Chinese word dependency analysis
指導教授:李御璽李御璽引用關係楊接期楊接期引用關係
指導教授(外文):Yue-Shi LeeJie-Chi Yang
學位類別:博士
校院名稱:國立中央大學
系所名稱:資訊工程研究所
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:2007
畢業學年度:96
語文別:英文
論文頁數:144
中文關鍵詞:詞性標註中文斷詞中文詞相依性剖析機器學習
外文關鍵詞:part-of-speech taggingword segmentationChinese dependency parsingmachine learning
相關次數:
  • 被引用被引用:0
  • 點閱點閱:149
  • 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:0
本論文提出一個整合性之中文語法相依性分析之架構,並包含了中文詞切割及詞性標注等問題。我們首先討論中文斷詞與詞性標注等問題,並且探討將此問題轉換為一個常見的序列分析分類的過程。然要訓練一個序列分析器,我們也研究了幾個目前常用而且效果很好的方法。在我們的實驗中發現最好的一個方法-CRF要優於其他分析器,但其缺點就是慢而且與類別數量成二次方成長,這使得中文詞性標注的問題無法在實際上能處理。為克服此問題,我們提出了一個結合CRF與SVM的二階段模型,結合CRF高效能的優點,並以SVM快速且準確的特性補足其效率問題。實驗證明我們的方法要明顯優於其他方法(包含CRF, 96.2 vs. 95.9 in F-measure)。 在公認的中文斷詞語料(SIGHAN-3)上,我們的方法也達到幾乎最佳的結果。
藉由二階段中文詞標注,文章中的詞彙與其詞性都能以此切分。因此,我們使用這詞性分析器所分出的詞彙用來進行下一階段的詞性語法相依性分析。為了使文法分析結果更上一層樓,我們也整合頂層與底層的句法關係並列入考量。同時,本研究也與目前公認最好的詞法相依性分析方法比較。實驗結果顯示,本研究的方法,不但比其他方法準確,而且訓練與測試時間要大大的減少。
此外,本研究也提出一個近似K-best 搜尋法來改善整體解析文法與斷詞之結果。此法的優點在於可以不須修改訓練模組,而在測試時對所有可能的候選一起列入考慮,以決定最後之文法解析結果。
This thesis proposes a unified Chinese dependency parsing framework where the word segmentation and POS-tagging were included. We first discuss the issue of the Chinese word segmentation and part-of-speech tagging. Then we exploit the conversion of Chinese POS tagging as sequential chunk-labeling problem and treat it as the conventional sequential chunk labeling tasks. To train a sequential labeler several classification algorithms are investigated. However, the observed best method-CRF yields superior but slower performance than the other approaches which make the POS tagging intractable. To circumvent this, we propose a two-pass sequential chunk labeling model to combine CRF with SVM. The experimental result showed that the two-pass learner achieves the best result than the other single-pass methods (96.2 vs. 95.9). In the well-known benchmark corpus (SIGHAN), our method also showed very competitive performance.
By means of the two-pass Chinese POS tagging, the words associated with their part-of-speech labels could be auto-segmented and labeled. We therefore employ the auto-segmented words for dependency parsing. To enhance the performance our parser integrates both top-down and bottom-up syntactic information. Meanwhile, we also compare with current state-of-the-art dependency parsers. The experimental result showed that our method is not only more accurate but also spends much less training and testing time than the other approaches.
In addition, an approximate K-best reranking method is designed to improve the overall dependency parse and also for word segmentation results. The advantage is that one can independently train these modules, while taking the global parse into consideration through the K-best selection.
Chapter 1 Introduction 1
1.1 BACKGROUND 1
1.2 MOTIVATION 2
1.3 PROBLEM SETTINGS 4
1.4 ROADMAP 5
Chapter 2 Prior Works 7
2.1 PHRASE CHUNKING 7
2.2 CHINESE WORD SEGMENTATION AND PART-OF-SPEECH TAGGING 8
2.3 DEPENDENCY PARSING 10
2.4 BENCHMARK CORPUS 13
Chapter 3 Statistical Machine Learning Approaches 15
3.1 SUPPORT VECTOR MACHINES 15
3.1.1 Multiclass SVMs 17
3.2 HIDDEN MARKOV MODELS 19
3.3 TRANSFORMATION-BASED ERROR-DRIVEN LEARNING 21
3.4 MAXIMUM ENTROPY MODELS 23
3.5 CONDITIONAL RANDOM FIELDS 24
3.6 SUMMARY 27
Chapter 4 A Sequential Chunk Labeling Framework for Chinese Word Segmentation and POS Tagging 29
4.1 REPRESENTATION 29
4.2 A SEQUENTIAL CHUNK LABELING FRAMEWORK FOR CHINESE WORD SEGMENTATION AND PART-OF-SPEECH TAGGING 30
4.3 EVALUATION METRICS 33
4.4 SETTINGS 34
4.5 EXPERIMENTAL RESULTS 36
4.6 APPLY TO SIGHAN BAKE-OFF 3 43
Chapter 5 Chinese Dependency Parsing 47
5.1 RELATED WORK 47
5.2 PARSING FRAMEWORK 49
5.3 PROBLEM SETTING 51
5.4 PARSING ALGORITHMS 52
5.5 BOTTOM-LEVEL INFORMATION: NEIGHBOR PARSING 66
5.6 TOP-LEVEL INFORMATION: ROOT PARSING 67
5.7 K-BEST RERANKING 68
Chapter 6 Experimental Results for Chinese Dependency Parsing 73
6.1 EVALUATION METRICS 73
6.2 SETTINGS 75
6.3 COMPARED PARSERS 77
6.4 RESULTS 79
6.5 DISCUSSIONS AND ERROR ANALYSIS 87
Chapter 7 Application to Multilingual Dependency Parsing 91
7.1 DEPENDENCY PARSING SHARED TASK 91
7.2 PARSING MODELS WE USED IN CONLL-2006 92
7.3 EXPERIMENTAL RESULTS ON CONLL-2006 95
7.4 DISCUSSION OF CONLL-2006 97
7.5 PARSING MODELS WE USED IN CONLL-2007 100
7.6 EXPERIMENTAL RESULTS ON CONLL-2007 103
7.7 DISCUSSION OF CONLL-2007 104
Chapter 8 Conclusions and Future Work 107
8.1 CONCLUSION 107
8.2 FUTURE DIRECTION 108
Bibliography 110
Appendix A The Chinese Treebank POS Tagset 121
Appendix B Chinese Treebank Phrase Tagset 123
Appendix C Pilot Study on Chinese and English Phrase Chunking 125
Appendix D Headword Rules for Chinese Treebank Conversion 129
[1]S. Abney. Parsing by chunks. In Principle-based parsing: Computation and Psycholinguistics, pages 257-278, 1991.
[2]R. K. Ando and T. Zhang. A high-performance semi-supervised learning method for text chunking. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), pages 1-9. 2005.
[3]G. Attardi. Experiments with a multilanguage non-projective dependency parser. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), pages 166-170, 2006.
[4]G. Attardi, F. Dell''Orletta, M. Simi, A. Chanev and M. Ciaramita. 2007. Multilingual Dependency Parsing and Domain Adaptation using DeSR. In Joint Conference on Empirical Methods in Natural Language Processing and Conference on Computational Natural Language Learning (EMNLP-CoNLL), 2007.
[5]S. J. Benson and J. J. Moré. A limited memory variable metric method for bound constraint minimization. Technical Report ANL/MCS-P909-0901, Argonne National Laboratory, 2001.
[6]A. Berger, A. Della Pietra, and J. Della Pietra. A maximum entropy approach to natural language processing. Computational Linguistics, 22(1):39-71, 1996.
[7]D. M. Bikel and D. Chiang. Two statistical parsing models applied to the Chinese Treebank. In Proceedings of the Chinese language processing workshop, pages 1-6, 2000.
[8]J. Blitzer, R. McDonald, and F. Pereira. Multilingual dependency parsing with a two-stage discriminative parser. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), pages 216-220, 2006.
[9]T. Brants. Cascaded markov models. In Proceedings of the Conference on European Chapter of the Association for Computational Linguistics (EACL) pages 118-125, 1999.
[10]T. Brants. TNT - A Statistical part-of-speech tagger. In Proceedings of the Conference on Applied Natural Language Processing (ANLP), 2000.
[11]E. Brill. Transformation-based error-driven learning and natural language processing: a case study in part of speech tagging. Computational Linguistics, 21(4), 543-565, 1995.
[12]E. Briscoe and J. Carroll. Generalised probabilistic lr parsing of natural language (corpora) with unification-based grammars. Computational Linguistics, 19(1): 25-29, 1993.
[13]S. Buchholz, E. Marsi, A. Dubey, and Y. Krymolowski. 2006. CoNLL-X Shared Task on Multilingual Dependency Parsing, In Proceedings of Conference on Computational Natural Language Learning (CoNLL), pages 149-164, 2006.
[14]C. J. C. Burges. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, pages 121-167, 1998.
[15]X. Carreras, L. Marquez, and J. Castro. Filtering-ranking perceptron learning for partial parsing. Machine Learning, 60: 41-71, 2005.
[16]M. W. Chang, Q. Do, and D. Roth. Multilingual dependency parsing: a pipeline approach. In Recent Advances in Natural Language Processing (RANLP), pages 195-204, 2006.
[17]E. Charniak. A maximum-entropy-inspired parser. In Proceedings of the Conference on North American Chapter of the Association for Computational Linguistics (ANLP-NAACL), pages 132-139, 2000.
[18]E. Charniak and M. Johnson. Coarse-to-fine n-best parsing and MaxEnt discriminative reranking. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), pages 173-180, 2005.
[19]C. Chelba and A. Acero. Adaptation of maximum entropy capitalizer: Little data can help a lot. In Proceedings of the Empirical. Methods in Natural Language Processing (EMNLP), 2004.
[20]K. J. Chen, C. R. Huang, F. Y Chen, C. C. Luo, M. C. Chang, and C. J. Chen. Sinica Treebank: design criteria, representational issues and implementation. Building and Using Parsed Corpora, Kluewer, 2004.
[21]S. Chen and R. Rosenfeld. A gaussian prior for smoothing maximum entropy models. Technical Report CMU-CS-99-108, Carnegie Mellon University, 1999.
[22]Y. Cheng, M. Asahara, and Y. Matsumoto, Deterministic dependency analyzer for Chinese. In Proceedings of the First International Joint Conference on Natural Language Processing (IJCNLP), pages 135-140, 2004.
[23]Y. Cheng, M. Asahara, and Y. Matsumoto. Machine learning-based Dependency Analyzer for Chinese. In Proceedings of the International Conference on Chinese Computing (ICCC), pages 66-73, 2005a.
[24]Y. Cheng, M. Asahara, and Y. Matsumoto, Chinese Deterministic Dependency Analyzer: Examining Effects of Global Features and Root Node Finder. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, pages 17-24, 2005b.
[25]Y. Cheng, M. Asahara and Y. Matsumoto. Multi-lingual Dependency Parsing at NAIST. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), pages 191-195, 2006.
[26]S. Clark, J. R. Curran, and M. Osborne. Bootstrapping POS taggers using unlabelled data. In Proceedings of the Meeting of North American Chapter of Association for Computational Linguistics (NAACL), pages 49-55, 2003.
[27]M. Collins, Head-driven statistical models for natural language processing. PhD thesis, University of Pennsylvania, 1999.
[28]T. H. Cormen, C. E. Leiserson, R. L. Rivest, and C. Stein. Introduction to algorithms: second edition. McGraw-Hill Higher Education, 2002.
[29]S. Corston-Oliver, A. Aue, K. Duh, and E. Ringger, Multilingual dependency parsing using Bayes point machines. In Proceedings of the Meeting of North American Chapter of Association for Computational Linguistics (NAACL), pp. 160-167, 2006.
[30]K. Crammer and Y. Singer. On the algorithmic implementation of multiclass kernel-basd vector machines. Journal of Machine Learning Research, 2: 265-292, 2001.
[31]K. Crammer and Y. Singer. Ultraconservative online algorithms for multiclass problems, Journal of Machine Learning Research, 3: 951-991, 2003.
[32]H. Cui, R. Sun, K. Li, M. Kan, and T. Chua. Question answering passage retrieval using dependency relations. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval, pages 400-407, 2005.
[33]W. Daelemans, J. Zavrel, P. Berck, and S. Gillis. TiMBLL MBT: a memory-mased part of speech tagger-generator. In Proceedings of Workshop on Very Large Corpora (WVLC), pages 14-27, 1996.
[34]H. Daume and D. Marcu. Domain adaptation for statistical classifiers. Journal of Artificial Intelligence Research, 26: 101-126, 2006.
[35]T. G. Dietterich. Approximate statistical tests for comparing supervised classification learning algorithms. Neural computation, 10: 1895-1923, 1998.
[36]D. Duchier and R. Debusmann. Topological dependency parsing: a constraint-based account of linear precedence. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), pages 180-187, 2001.
[37]J. Eisner. Bilexical grammars and their cubic-time parsing algorithms. In Bunt and Nijholt (eds.) Advances in Probabilistic and Other Parsing Technologies, Kluwer, 2000.
[38]J. Eisner. Three New Probabilistic Models for Dependency Parsing: An Exploration. In Proceedings of International Conference on Computational Linguistics (COLING), 1996.
[39]D. Elworthy. Does Baum-Welch re-estimation help taggers? In Proceedings of the Conference on Applied Natural Language Processing (ANLP), pages 53-58, 1994.
[40]T. Emerson. The second international Chinese word segmentation bakeoff. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, 2005.
[41]R. E. Fan, P. H. Chen, and C. J. Lin. Working set selection using the second order information for training SVM, Journal of Machine Learning Research 6: 1889-1918, 2005.
[42]R. Florian, H. Hassan, A. Ittycheriah, H. Jing, N. Kambhatla, X. Luo, N. Nicolov, and S. Roukos. A statistical model for multilingual entity detection and tracking. In Proceedings of the Meeting of North American Chapter of Association for Computational Linguistics (NAACL), 2004.
[43]R. Florian, J.C. Henderson, and G. Ngai. Coaxing confidence from an old friend: Probabilistic classifications from transformation rule lists. In Proceedings of the Empirical. Methods in Natural Language Processing (EMNLP), 2000.
[44]R. Florian, A. Ittycheriah, H. Jing, and T. Zhang. Named entity recognition through classifier combination. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), pages 168-171, 2003.
[45]P. Fung, G. Ngai, Y. Yang, and B. Chen. A Maximum-entropy Chinese parser augmented by transformation-based learning. ACM Transactions on Asian Language Information Processing, 3(2): 159-168, 2004.
[46]H. Gaifman. Dependency systems and phrase-structure systems. Information and Control, 8: 304-337.
[47]J. Gao, J. Y. Nie, G. Wu, and G. Cao. Dependence language model for information retrieval, In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval, pages 172-179, 2004.
[48]X. Ge, W. Pratt, and P. Smyth. Discovering Chinese words from unsegmented text. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval, 1999.
[49]J. Giménez, and L. Márquez. Fast and accurate Part-of-Speech tagging: the SVM approach revisited. In Recent Advances in Natural Language Processing (RANLP), pages 158-165, 2003.
[50]C. L. Goh, M. Asahara, and Y. Matsumoto. Chinese word segmentation by classification of characters. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, pages 57-64, 2004.
[51]K. Hacioglu. Semantic role labeling using dependency trees. In Proceedings of International Conference on Computational Linguistics (COLING), pages 1273-1276, 2004.
[52]J. Hall, J. Nivre, and J. Nilsson, Discriminative classifiers for deterministic dependency parsing. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), pp. 316-323, 2006.
[53]D. Hays. Dependency theory: a formalism and some observations. Language, 40: 511-525, 1964.
[54]H. Isozaki, H. Kazawa, and T. Hirao. A deterministic word dependency analyzer enhanced with preference learning. In Proceedings of International Conference on Computational Linguistics (COLING), pages 275-281, 2004.
[55]T. K. Huang, R. C. Weng, and C. J. Lin. Generalized bradley-terry models and multi-class probability estimates, Journal of Machine Learning Research, 7: 85-115, 2006.
[56]R. Hudson. Word grammar. Basil Blackwell, 1984.
[57]M. Jin, M. Y. Kim, and J. H. Lee. Two-phase shift-reduce deterministic dependency parser of Chinese. In Proceedings of the Second International Joint Conference on Natural Language Processing (IJCNLP), 2005.
[58]T. Joachims. Text categorization with support vector machines: learning with many relevant features. In Proceedings of the European Conference on Machine Learning (ECML), pages 137-142, 1998.
[59]J. Kazama and J. Tsujii. Evaluation and extension of maximum entropy models with inequality constraints. In Proceedings of the Empirical. Methods in Natural Language Processing (EMNLP), pages 137-144, 2003.
[60]S. Keerthi and D. DeCoste. A modified finite Newton method for fast solution of large scale linear SVMs. Journal of Machine Learning Research. 6: 341-361, 2005.
[61]C. Kit and Y. Wilks. Unsupervised learning of word boundary with description length gain. In Proceedings CoNLL99 ACL Workshop, 1999.
[62]A. Klautau, N. Jevtic, and A. Orlitsky. On nearest-neighbor error-correcting output codes with application to all-pairs multiclass support vector machines. Journal of Machine Learning Research, 4: 1-15, 2003.
[63]D. Klein and C. D. Manning. A generative constituent-context model for improved grammar inductrion. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), pages 128-135, 2002.
[64]U. Kreßel. Pairwise classification and support vector machines. Advances in Kernel Methods: Support Vector Learning, pages 255-268, 1999.
[65]T. Kudo and Y. Matsumoto. Use of support vector learning for chunk identification. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), pages 142-144, 2000.
[66]T. Kudo and Y. Matsumoto. Chunking with support vector machines. In Proceedings of the Meeting of North American Chapter of Association for Computational Linguistics (NAACL) In Proceedings of the Meeting of North American Chapter of Association for Computational Linguistics (NAACL), pages 192-199, 2001.
[67]T. Kudo and Y. Matsumoto. Fast methods for kernel-based text analysis. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), pages 24-31, 2003.
[68]T. Kudo and Y. Matsumoto. Appliying conditional random fields to Japanese morphological analysis. In Proceedings of the Empirical. Methods in Natural Language Processing (EMNLP), pages 230-237, 2004.
[69]O. Y. Kwong. Categorical fluidity in Chinese and its Implications for part-of-speech tagging. In Proceedings of the Conference on European Chapter of the Association for Computational Linguistics (EACL), pages 115-118. 2003.
[70]J. Lafferty, A. McCallum, and F. Pereira. Conditional random fields: probabilistic models for segmenting and labeling sequence data. In Proceedings of the International Conference on Machine Learning (ICML), pages 282-289, 2001.
[71]Y. S. Lee and Y. C. Wu. A robust multilingual portable phrase chunking system. Expert Systems with Applications, 33(3): 1-26, 2007.
[72]G. A. Levow. The third international Chinese word segmentation bakeoff: word segmentation and named entity recognition. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, pages 108-117, 2006.
[73]H. Lian. Chinese language parsing with maximum-entropy-inspired parser. Master''s thesis, Brown University, 2005.
[74]D. Liu and J. Nocedal. On the limited memory BFGS method for large-scale optimization. Mathematical Programming, 45:503-528, 1989.
[75]X. Luo. A maximum entropy Chinese character-based parser. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2003.
[76]J. Ma, Y. Zhang, and S. Li, A statistical dependency parser of Chinese under small training data. In Proceedings of the 1st International Joint Conference of Natural Language Processing, pp. 1-5, 2004.
[77]R. Malouf. A comparison of algorithms for maximum entropy parameter estimation. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), pages 49-55, 2002.
[78]H. Maruyama. Structural disambiguation with constraint propagation. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), 1990.
[79]D. McClosky, E. Charniak, and M. Johnson. Reranking and self-training for parser adaptation. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), 2006.
[80]R. McDonald, C. Krammer, and F. Pereira. Online large-margin training of dependency parsers. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), 2005.
[81]R. McDonald, K. Lerman, and F. Pereira. Multilingual dependency analysis with a two-stage discriminative. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), pages 216-220, 2006
[82]I. Mel’cuk. Dependency syntax: theory and practice. The SUNY Press, Albany, 1988.
[83]W. Menzel, and I. Schröder. Decision Procedures for Dependency Parsing Using Graded Constraints. In Workshops of the Processing of Dependency-based Grammars, 1998.
[84]A. Molina and F. Pla. Shallow parsing using specialized HMMs. Journal of Machine Learning Research, 2: 595-613, 2002.
[85]T. Nakagawa, T. Kudo, and Y. Matsumoto. Unknown word guessing and Part-of-Speech tagging using support vector machines. In Proceedings of the 6th Natural Language Processing Pacific Rim Symposium, pages 325-331, 2001.
[86]H. T. Ng and J. K. Low. Chinese part-of-speech tagging. one-at-a-time or all-at-once? word-based or character-based? In Proceedings of the Empirical. Methods in Natural Language Processing (EMNLP), 2004.
[87]J. Nivre. An efficient algorithm for projective dependency parsing. In Proceedings of the International Workshop on Parsing Technology (IWPT), pages 149-160, 2003.
[88]J. Nivre and J. Nilsson. Pseudo-projective dependency parsing. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), pages 99-106, 2005.
[89]J. Nivre, J. Hall, J. Nilsson, G. Eryigit, and S. Marinov. Labeled pseudo-projective dependency parsing with support vector machines. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), pages 221-225, 2006.
[90]J. Nivre, J. Hall, S. Kübler, R. McDonald, J. Nilsson, S. Riedel, and D. Yuret. The CoNLL 2007 shared task on dependency parsing. In Joint Conference on Empirical Methods in Natural Language Processing and Conference on Computational Natural Language Learning (EMNLP-CoNLL), 2007.
[91]J. Nivre, J. Hall, and J. Nilsson. Memory-based dependency parsing. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), 2004.
[92]P. Pantel and D. Lin. Discovering word senses from text. In Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. Pages 613-619, 2002.
[93]J.C. Platt, N. Cristianini, and J. Shawe-Taylor, Large margin dags for multiclass classification. Advanced in Neural Information Processing Systems, 12: 547-553, 2000.
[94]J. C. Platt. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Large Margin Classifiers, MIT Press, 1999.
[95]L. Rabiner. A tutorial on hidden markov models and selected applications in speech recognition. In Proceedings of IEEE, 77(2):257-286, 1989.
[96]L. A. Ramshaw and M. P. Marcus. Text chunking using transformation-based learning. In Proceedings of Workshop on Very Large Corpora (WVLC), pages 82-94, 1995.
[97]R. Rifkin and A. Klautau. In defense of one-vs-all classification. Journal of Machine Learning Research, 5: 101-141, 2004.
[98]A. Ratnaparkhi. A linear observed time statistical parser based on maximum entropy models. In Proceedings of the Second Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1-10, 1997.
[99]B. Roark and M. Bacchiani. Supervised and unsupervised PCFG adaptation to novel domains. In Proceedings of the Meeting of North American Chapter of Association for Computational Linguistics (NAACL), 2003.
[100]K. Sagae, A. Lavie, and B. MacWhinney. Automatic measurement of syntactic development in child language. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2005.
[101]Y. Seginer. Fast unsupervised incremental parsing. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), pages 384-391, 2007.
[102]F. Sha and F. Pereira. Shallow parsing with conditional random fields. In Proceedings of the Meeting of North American Chapter of Association for Computational Linguistics (NAACL), 2003.
[103]H. Shen and A. Sarkar. Voting between multiple data representations for text chunking. In Proceedings of the Meeting of the Canadian Society for Computational Intelligence, pages 389-400, 2005.
[104]D. D. K. Sleator and D. Temperley. Parsing English with a link grammar. In Proceedings of the International Workshop on Parsing Technology (IWPT), 1993.
[105]R. Sproat and T. Emerson. The first International Chinese word segmentation Bakeoff. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, 2003.
[106]M. Steedman, R. Hwa, S. Clark, M. Osborne, A. Sarkar, J. Hockenmaier, P. Ruhlen, S. Baker, and J. Crim, Example selection for bootsrapping statistical parsers. In Proceedings of the Meeting of North American Chapter of Association for Computational Linguistics (NAACL), pages 157-164, 2003.
[107]W. Sun, and J. Chen, A multi-class classifier based on SVM decision tree. IEEE Computational Intelligence Society Electronic Letter, in press.
[108]F. Takahashi, and S. Abe, Decision-tree-based multicalss support vector machines. In Proceedings of the International Conference on Neural Information Processing Systems (NIPS), 2: 1418-1422, 2002.
[109]P. Tapanainen and T. Järvinen. A non-projective dependency parser. In Proceedings of the Conference on Applied Natural Language Processing (ANLP), 1997.
[110]L. Tesniere. Element de syntaxe structurale. Paris: Editions Klincksieck, 1959.
[111]I. Titov and J. Henderson. Porting statistical parsers with data-defined kernels. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), 2006.
[112]E. F. Tjong Kim Sang. Transforming a chunker to a parser. Computational Linguistics in the Netherlands, pages 177-188, 2001
[113]E. F. Tjong Kim Sang, and S. Buchholz. Introduction to the CoNLL-2000 shared task: chunking. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), pages 127-132, 2000.
[114]E. F. Tjong Kim Sang and J. Veenstra. Representing text Chunks. In Proceedings of the Conference on European Chapter of the Association for Computational Linguistics (EACL), pages 173-179, 1999.
[115]M. Tomita. The generalized lr parser/compiler – version 8.4. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), pages 59-63, 1990.
[116]H. Tseng, P. Chang, G. Andrew, D. Jurafsky, and C. Manning. A conditional random field word segmenter. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, pages 168-171, 2005.
[117]T. Tsochantaridis, T. Joachims, T. Hofmann, and Y. Altun, Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research, 6: 1453-1484, 2005.
[118]V. N. Vapnik, The nature of statistical learning theory. Springer, 1995.
[119]V. Vural, and J. D. Dy, A hierarchical method for multi-class support vector machines, In Proceedings of the International Conference on Machine Learning (ICML), pages 831-838, 2004.
[120]Q. I. Wang, D. Lin, and D. Schuurmans, Simple training of dependency parsers via structured boosting. In Proceedings of International Joint Conference on Artificial Intelligence, pp. 1756-1762, 2007.
[121]M. Wang and Y. Shi. Using part-of-speech reranking to improve Chiense word segmentation. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, pages 205-208, 2006.
[122]Y. C. Wu, C.H. Chang, and Y. S. Lee, A general and multi-lingual phrase chunking model based on masking method. Lecture Notes in Computer Science (LNCS): Computational Linguistics and Intelligent Text Processing, 3878: 144-155, 2006.
[123]Y. C. Wu and C.H. Chang. Efficient text chunking using linear kernel with mask method. Knowledge Based Systems, 20(3): 209-219, 2007.
[124]Y. C. Wu, Y. S. Lee, and J. C. Yang. The exploration of deterministic and efficient dependency parsing. In Proceedings of Conference on Computational Natural Language Learning (CoNLL), pages 241-245, 2006.
[125]Y. C. Wu, J. C. Yang, and Q. X. Lin. 2006. Description of the NCU Chinese word segmentation and named entity recognition system for SIGHAN bakeoff 2006. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, pages 209-212, 2006.
[126]Y. C. Wu, J. C. Yang, and Y. S. Lee, and S. J. Yen, Efficient and robust phrase chunking using support vector machines. Lecture Notes in Computer Science (LNCS): Asia Information Retrieval Symposium (AIRS), 4182: 350-36, 2006.
[127]Y. C. Wu, J. C. Yang, and Y. S. Lee, Multilingual deterministic dependency parsing framework using modified finite Newton method support vector machines. In Joint Conference on Empirical Methods in Natural Language Processing and Conference on Computational Natural Language Learning (EMNLP-CoNLL), 2007.
[128]Y. C. Wu, J. C. Yang, and Y. S. Lee. An approximate approach for training polynomial kernel SVMs in Linear Time. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), Poster, 2007.
[129]F. Xia, and L. Cheung. Features, bagging, and system combination for the Chinese POS tagging task. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, pages 25-32, 2006.
[130]F. Xia, M. Palmer, N. Xue, M. E. Okurowski, J. Kovarik, F. D. Chiou, S. Huang, T. Kroch, and M. Marcus. Developing guidelines and ensuring consistency for Chinese text annotation. In Proceedings of the second International Conference on Language Resources and Evaluation (LREC), 2000.
[131]J. Xu, S. Miller, and R. Weischedel. A statistical parser for Chinese. In Proceedings Human Language Technology Workshop, 2002.
[132]N. Xue and S. P. Converse. Combining classifiers for Chinese word segmentation. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, pages 63-70. 2002.
[133]N. Xue, F. D. Chiou, and M. Palmer. The Chinese Treebank: phrase structure annotation of a large corpus. Natural Language Engineering, 11(2): 207-238, 2005.
[134]H. Yamada and Y. Matsumoto. Statistical dependency analysis with support vector machines. In Proceedings of the 8th International Workshop on Parsing Technologies (IWPT), pages 195-206, 2003.
[135]Y. Yang and X. Liu. A re-examination of text categorization methods. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval, pages 42-49, 2005.
[136]T. Zhang, F. Damerau, and D. Johnson. Text chunking based on a generalization Winnow. Journal of Machine Learning Research, 2: 615-637, 2002.
[137]T. Zhang, F. Damerau, and D. Johnson. Text chunking using regularized Winnow. In Proceedings of the Annual Meetings of the Association for Computational Linguistics (ACL), pages 539-546, 2001.
[138]G. D. Zhou and J. Su, A Chinese efficient analyzer integrating word segmentation, part-of-speech tagging, partial parsing and full parsing. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, pages 78-83, 2003.
[139]G. D. Zhou. Chunking-based Chinese word tokenization. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, pages 188-191, 2003.
[140]H. Zhou, C. N. Huang, and M. Li. An improved word segmentation system with conditional random fields. In Proceedings of the SIGHAN Workshop on Chinese Language Processing Workshop, pages 162-165, 2006.
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