Automatic word spacing using probabilistic models based on character n-grams

IEEE Intelligent Systems

Volumn 22, Issue 1, 2007, Pages 28-35

  Lee, Do Gil ^a,b   Rim, Hae Chang ^a   Yook, Dongsuk ^a  

^a Korea University   (South Korea)

^b Venture Town Bldg ^*  (South Korea)

Author keywords

[No Author keywords available]

Indexed keywords

AUTOMATIC WORD SPACING; NATURAL LANGUAGES; PROBABILISTIC MODELS; SPACING ERRORS;

ERROR CORRECTION; HIDDEN MARKOV MODELS; MATHEMATICAL MODELS; NATURAL LANGUAGE PROCESSING SYSTEMS; WORD PROCESSING;

PROBABILISTIC LOGICS;

EID: 33847611998     PISSN: 15411672     EISSN: None     Source Type: Journal    
DOI: 10.1109/MIS.2007.4     Document Type: Article

References (13)

1. E. Charniak et al., "Equations for Part-of-Speech Tagging," Proc. 11th Nat'l Conf. Artificial Intelligence (AAAI 93), AAAI Press, 2003, pp. 784-789.
2. D. Merialdo, "Tagging English Text with a Probabilistic Model," Computational linguistics, vol. 20, no. 2, 1994, pp. 155-172.
3. L. Rabiner. "An Introduction to Hidden Markov Models," IEEE ASSP Magazine, vol. 3, no. 1, 1986, pp. 4-16.
4. J.-H. Choi, "Automatic Korean Spacing Words Correction System with Bidirectional Longest Match Strategy," Proc. 9th Conf. Hangul and Korean Information. Processing, Korea Information Science Soc., 1997, pp. 145-151.
5. S.-S. Kang, "Automatic Word-Segmentation for Hangul Sentences." Proc. 10th Conf. Hangul and Korean Information Processing, Korea Information Science Soc., 1998, pp. 137-142.
6. S.-S. Kang, "Eojeol-Block Bidirectional Algorithm for Automatic Word Spacing of Hangul Sentences." J. Korea Information Science Soc., vol. 27, no. 4, 2000, pp. 441-447.
7. K.-S. Kim, H.-J. Lee, and S.-J. Lee, "Three-Stage Spacing System for Korean in Sentence with No Word Boundaries," J. Korea Information Science Soc., vol. 25, no. 12, 1998, pp. 1838-1844.
8. Y.-M. Chung and J.-Y. Leo, "Automatic Word-Segmentation at Line-Breaks for Korean Text Processing." Proc. 6th Conf. Korea Soc. for Infor mation Management, Korea Soc. for Information Management, 1999, pp. 21-24.
9. N.-Y. Jeon and H.-R. Park, "Automatic Word-Spacing of Syllable DiGram Information for Korean OCR Postprocessing," Proc. 12th Conf. Hangul and Korean Information Processing, Korea Information Science Soc., 2000, pp. 95-100.
10. S.-S. Kang and C.-W.Woo, "Automatic Segmentation of Words Using Syllable Bigram Statistics," Proc. 6th Natural Language Processing Pacific Rim Symp., Information Processing Soc. of Japan, 2001, pp. 729-732.
11. K. Shim, "Automated Word-Segmentation for Korean Using Mutual Information of Syllables." J. Korea Information Science Soc., vol. 23, no. 9, 1996, pp. 991-1000.
12. J.-H. Shin and H.-R. Park, "A Statistical Model for Korean Text Segmentation Using Syllable-Level Digrams." Proc. 9th Conf. Hangul and Korean Information Processing, Korea Information Science Soc., 1997, pp. 255-260.
13. T. Brants, "TnT - A Statistical Part-of-Speech Tagger." Proc. 6th Applied Natural Language Processing Conf. (ANLP 00), Assoc. for Computational Linguistics, 2000, pp. 224-231.